See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/369039446

Insights into Search Engine Optimization using Natural Language Processing

and Machine Learning

Article in International Journal of Advanced Computer Science and Applications · January 2023
DOI: 10.14569/IJACSA.2023.0140211

CITATIONS READS
0 394

1 author:

Vinutha Ms
Dr. Ambedkar Institute of Technology
9 PUBLICATIONS 12 CITATIONS

SEE PROFILE

All content following this page was uploaded by Vinutha Ms on 18 April 2023.

The user has requested enhancement of the downloaded file.

 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

Insights into Search Engine Optimization using

Natural Language Processing and Machine Learning
Vinutha M S1, M C Padma2
Research Scholar, Department of Computer Science & Engineering, P E T Research Centre, Mandya,
University of Mysore, Mysuru, India1
Professor, Department of Computer Science & Engineering, PESCE, Mandya, India2

Abstract—Among the potential tools in digital marketing, objects to ensure that it is well-chosen by the target customer in
Search Engine Optimization (SEO) facilitates the use of the on-page SEO process. On the other hand, the backlinks'
appropriate data by providing appropriate results according to optimization process is carried out at the backend of the
the search priority of the user. Various research-based webpage in the off-page process of SEO. This form of SEO
approaches have been developed to improve the optimization mainly focuses on establishing relationships among the content
performance of search engines over the past decade; however, it to reach its appropriate customer. Currently, a specific set of
is still unclear what the strengths and weaknesses of these programs called bots are used to perform crawling within the
methods are. As a result of the increased proliferation of webpage using existing search engines, viz. Bing/Google [8].
Machine Learning (ML) and Natural Language Processing
This operation aggregates information associated with the
(NLP) in complex content management, there is potential to
target web contents, placing them in the form of an index. The
achieve successful SEO results. Therefore, the purpose of this
paper is to contribute towards performing an exhaustive study
web contents are analyzed within the index by such algorithms
on the respective NLP and ML methodologies to explore their considering a massive number of signals or ranking values.
strengths and weaknesses. Additionally, the paper highlights This is done to ensure the availability of the page at the top of
distinct learning outcomes and a specific research gap intended query hits. The prime target of such a form of the search
to assist future research work with a guideline necessary for algorithm is to evolve up with a highly authoritative page to
optimizing search engine performance. offer a superior experience of searching by the user.
Irrespective of all the efforts towards improving the
Keywords—Search engine optimization; google search; natural performance of SEO tools, there are still serious concerns that
language processing; machine learning; recommendation have posed as an impediment, viz. i) inaccurate formulation of
webpage index, ii) identifying and constructing a precise
I. INTRODUCTION keyword, iii) structuring the wrong webpage/contents not in
In the present era of the competitive market, every line with the target topic, iv) internal linking to be highly
organization and individual intends to ensure that their incoherent, v) slower /fluctuating uploading performance of the
information reaches the right clients in minimal effort. web page in different computing device [9][10]. Therefore, this
Stakeholders also need to have a clear insight into their paper identifies the potential of using Natural Language
upcoming business demands. From all these perspectives, Processing (NLP) and Machine Learning (ML) approaches to
business products and services are usually maintained via improve the performance of SEO. The paper contributes to
websites. This target is met by using Search Engine potential learning outcomes from existing literature. Further, it
Optimization (SEO), which facilitates carrying out the also contributes towards identifying significant research gaps
operation to assist the client webpage or its contents to offer extracted from existing techniques to improve SEO
higher ranks on the standard platform of Google [1]. The prime performance.
distinction between paid advertisement and SEO is that SEO
The paper's organization is as follows: Section II discusses
uses an organic methodology to generate ranking scores [2][3].
the fundamental information about SEO, followed by
It will eventually mean that a user will not be required to pay to
reviewing existing research practices of SEO with NLP in
be in that environment of using SEO [4]. In simplified form,
Section III. Section IV discusses ML practices used in SEO
the user of SEO tools identifies and extracts suitable content
while Section V discusses existing SEO tools. A discussion of
from a target webpage and optimizes it so that the webpage
existing research trends of SEO is carried out in Section VI,
always appears at the top of google searches [5]. SEO tools,
while the research gap is highlighted in Section VII. Section
therefore, assist in making higher visibility of the webpage and
VIII makes discussion about the results and research
offers a higher probability of reaching the maximum number of
implications. Section IX finally concludes the paper with
customers. There standard operational taxonomy of SEO is of
significant learning outcomes followed by a briefing of future
two types, i.e., on-page and off-page process SEO [6][7].
work to be carried out.
Basically, the ranking associated with the webpage can be
improved by appropriately building the web content using an II. INSIGHTS ON SEO
on-page process of SEO. This process essentially includes
constructing higher-quality content, generating appropriate This section presents insights into SEO or Website
keywords, managing meta-tags, and enhancing the different positioning. Firstly, a brief description of SEO followed by a

86 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

working principle of a search engine is discussed to understand

the intrinsic mechanism of SEO. Further, factors affecting
website posting are briefly discussed, and finally, this section
discusses challenges in SEO.
A. Search Engine Optimization
SEO is an act that includes a series of professional
activities. These activities include the practice of improving the
structure of content, thereby increasing visibility in search
engines and gaining a large amount of traffic to the website
[11]. Common SEO practices include rich content creation,
keyword optimization, and link building. Thus, SEO is a
powerful mechanism for advancing search engine algorithms to
come up with the most relevant and appropriate web content
and improve the website's ranking (in an organic way) in Fig. 2. Content querying and retrieval
search results, ultimately boosting marketability and increasing
sales. Through the search engine interface, the user provides a
search query. The search engine algorithm creates a URL
B. Work Principle of the Search Engine ranking list that matches the user's query to the index database
Search engines are obviously fundamental to the SEO based on contextual information. The search engine then
process, but many practitioners are unaware of how they work. displays a snippet subjected to the ranked URL to the user,
Therefore, one must first comprehend the basics of search who can browse and select to retrieve the corresponding
engines to learn SEO. A search engine is a service that enables content in its original form from the content database.
web search by performing three important tasks such as C. Factors Affecting Ranking and SEO Challenges
crawling, indexing, ranking, and recognizing items in the
system record or database corresponding to keywords specified The ranking of web content is influenced by many factors,
by the user [12-13]. Crawling enables search engines to including page relevance, temporal factors, and link weights
discover content, and indexing is a mechanism for obtaining [14]. A webpage's relevance is determined by its tags, density
web documents and maintaining replicas of the content they distribution, and identical keywords. Temporal aspects are
have visited. The ranking is mainly subject to search engines concerned with the oldness of websites, web contents and
mainly concerned with SEO operations. Fig. 1 depicts the webpages, the oldness of links, and the duration of domain
schematic architecture of the web content indexing process. registration. There are both internal and external links in the
contents. However, the external link is given more weight as it
is associated with significant factors such as quality, quantity,
relevancy, and repetition. A basic mechanism of SEO includes
almost all the core attributes of the above-discussed factors,
which can be numerically simplified and expressed as follows:
𝑆𝑒𝑜 = ∫ 𝐶 + 𝐿 + 𝐾 + 𝑂 (1)
Where, 𝐶 is the web content, 𝐿 denotes link, 𝐾 refers to
user keyword, 𝑂 represents other factors such as oldness of
website, or blog, server, web-design, URL, domain name, and
many more. All these factors have priority and should follow
priority order as mentioned in the above expression 1. Apart
from this, a few challenges associated with search engines
significantly affect the quality of the SEO process [15-16]. The
Fig. 1. Procedure of web content indexing first major issue is content spamming, a common method used
by unethical users to get their web pages in top results. The
Web content is retrieved using a WebCrawler (bot) that next issue is the article spinning, similar to scraping data using
stores the web content in a database of search engines. In specialized software that takes the copied original and
addition, web content is subject to data processing operations reproduces it as a new, original article for future use. The third
such as stemming, HTML tag, and stop-word removal. Later, issue is keyword stuffing, in which users reuse keywords like
indexing is done by search engines by generating direct and name, meta, head, etc., in different HTML tags and URL
replicating content, such as single words and their positional spammers. Furthermore, masquerading is an SEO technique
information on the search page. Furthermore, the search engine used to mislead users by redirecting them to a page that is
keeps the indexes in its index database. Fig. 2, depicts the different from the page crawled by search engines. Similarly, a
schematic architecture of the content querying and retrieval URL redirection is also a significant issue where the file is
procedure. redirected to a specific URL as soon as the user loads the site.

87 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

III. REVIEW OF SEO APPROACHES USING NLP requirement. Afterward, ontology classification is carried out
NLP is an area of ML that reveals the precise structure and to filter out the relevant subjects of the web content. Further
meaning of content. Modern websites are driven by algorithms, topic modeling is carried out using clustering, and statistical
which determine what they display in search results for specific computation is then carried to perform a re-ranking operation.
keywords. Using NLP in optimizing web content, it can be Semantic annotation for semi-structured data on a web page
expected that the content would reach the top of the search using header identification and object classification is
rankings. NLP can be used to analyze website content and presented by Zhang et al. [23]. The authors have designed a
optimize it for specific keywords or phrases. It can be used to description framework for annotating the data domain, and
identify and correct grammar and spelling errors, as well as to header identification is carried for annotating data objects on
generate content that is optimized for search engines. NLP the webpage. In addition, a feature vector is constructed for
techniques can also be used to analyze user queries and data objects which are left by header identification, and a
optimize website content to better match those queries neural network is then applied to perform semantic annotation.

Many research works are using the mechanism of NLP to Adoption of the latent semantic analysis for SEO is carried
achieve optimization in the search ranking. This section out by Horasan [24]. In this study, the keyword extraction
provides a brief highlight of the existing literature in the process from textual data with latent semantic analysis is
context of SEO. A research article presented by Killoran et al. performed to draw a relationship between documents/sentences
[17] has examined the influential factors that have a high and terms in the text using linear algebra. Uzun [25] suggested
impact on search ranking. It is reported that search ranking is a model-based string technique and DOM tree for content
formed on the basis of participants’ category, SEO experts, extraction. The string technique extracts information with the
search engine companies, and users. During the choice of HTML tags followed by the crawling process. The study of
keywords, the authors stated that the website's target audience Barrett et al. [26] presented an approach for searching large
and competitors have to be taken into account. The study video corpora for clips depicting human language queries
concludes that a combination of appropriate keyword expressed as sentences. In this study, a compositional
placement and link-building may yield the desired solution. semantics scheme is applied to encode refined meaning to
The study of Hajeer et al. [18], applied the NLP mechanism to extract the differences between two phrases with the same
overcome the limitations associated with the Porter algorithm words under a different context. Sal et al. [27] used a
used for term normalization and index time reduction in the disseminated cooperative cache based on evolutive summary
content retrieval systems. The authors have presented a counters to store approximate records of data accesses in a
different stemming technique to enhance content searching in search engine. Ghanbarpour and Naderi [28] examined the
an information retrieval system. The results claim ranking technique for keyword search according to the
improvement over existing technologies. Tsuei et al. [19] relevancy of the query over graph-structured data. Soltani et al.
devised a customized decision model based on the interview [29] employed an approach of semantic search engines to
and survey for SEO in internet marketing to boost the hit rate develop a different model for software signature search
of websites on the search page that satisfy users' requirements. engines. The authors have used the document-to-vector model
The finding of this study suggests that meta tags are the most to compute the signature and user query vectors.
influential factor that has a significant impact on the search The work of Dai et al. [30] suggested an efficient and
ranking. adaptive semantic-based keyword ranked search technique
The work of Luh et al. [20] aimed to examine the ranking using Doc2Vec for secured cloud data. Chen [31] focuses on
mechanism of the Google search engines from an SEO adopting a user interaction approach to control linguistic
viewpoint. The study suggested an estimation function for ambiguity to improve search engine outcomes. Zhang et al.
determining the score of query matching from a limited set of [32] have suggested a scheme to recognize the identifiers that
ranking factors. Further, re-ranking is carried out on the basis are associated with semantic text queries. In order to enhance
of obtained scores. The scope of the presented scheme is text queries, the authors have looked for keywords within class
evaluated based on the comparison of newly obtained ranks names from APIs with semantically related APIs. However, if
with the original ranks. Jenkins et al. [21] developed a model the corpus projects do not have sufficient vocabulary, this
for constructing text annotations for SEO. This model employs technique may not work as well. Calvillo et al. [33] presented
the Extreme Gradient Boosting algorithm for precise labeling an automated mechanism to classify and locate research
phrases. Also, logistic regression is considered in this model to information based on NLP. The implementation of this scheme
generalize the rank of aggregated annotations for clusters of focuses on cleaning data by removing aspects such as images
content. The study findings demonstrate that the presented and words that are not significant. The digital library was used
model increases the traffic to the web content by 1-2%. A to extract a percentage of the content from different articles
semantic architecture using web and data mining techniques is such as abstract, introduction, keywords, and other segments of
presented by Sharma et al. [22] for personalizing the the article, which help to perform the tests. Hamzei and
eCommerce search engine. The design and development of the Hakimpour [34] introduced a method for analyzing queries for
architecture consist of a series of implementation phases were, spatial search engines. This method employs iterative query
firstly, a query expansion is performed to transform the input segmentation identification of location-names and spatial
user query using NLP operations to understand the user relationships. Table I highlights the summary of the work
being discussed in this section.

88 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

TABLE I. SUMMARY OF SEO USING NLP TECHNIQUES

Authors Problems Techniques Advantage Limitation

Highlights influential factors, Only theoretical and
Killoran et al. [17] Search ranking Analytical study
and important suggestion analytical discussion
Related to Over-stemming
Hajeer et al. [18], Indexing time Stemming Outperforms Porter algorithm and only 2.3% of
improvement
Identification of factor affecting Highlighted significant website subjective opinions of
Tsuei et al. [19] Decision making system SEO factors
SEO driver decision-makers
Examine ranking of the Google Rank estimation function and Achieved the best SEO Considered limited set of
Luh et al. [20],
search engines re-ranking scheme effectiveness ranking factors
Understanding content to attract new XGBoost and Linear Higher dependency on more
Jenkins et al. [21] Increases traffic by 1-2 %
user regression keystrokes.
Ontology and Semantic Provides context-aware results Lacks statistical outcome
Sharma et al. [22] SEO for ecommerce
Approach and recommendations analysis to justify its usability
Identification for highlights of Annotation, Header Semantic annotation of semi- Only applicable for Chinese
Zhang et al. [23]
multimedia file system recognition, Neural network structured information language
Complies with the SEO criteria,
Latent semantic analysis and
Horasan [24] Adoption of knowledge contents helpful for who do not know No effective benchmarking
linear algebra
SEO
String technique and DOM Achieves time efficiency in web Dependency on various
Uzun [25] Time efficiency in Web scrapping
tree scraping manual process
searching large video corpora from Does not require any prior video
Barrett et al. [26] searching large video corpora Computationally in-efficient
text query annotation
understanding the underlying Flexible to support large data Domain-dependent
Sal et al. [27] Cooperative cache scheme
content of multimedia for analysis implementation
Ghanbarpour and Model-based ranking Improves the accuracy of the Only support single keyword
ranking search problem
Naderi [28] function ranking search
Soltani et al. [29] Digital security Paragraph Vector Model Achieves higher recall rate Computationally expensive
documents may be lost in the
Dai et al. [30] multi-keyword ranking search Doc2Vec model Simplified structural model
encrypted forms
Personalized topic search Quick response to user search Limited to English language
Chen [31] misinterprets the user query
system needs and used small dataset
If the corpus projects do not
Recognition of the identifiers that
Neural network model have sufficient vocabulary,
Zhang et al. [32] are associated with semantic text Provides a good scope
(CBOW) this technique may not work
query
as well.
Better performance in the does not capture position in
Calvillo et al. [33] locating research paper NLP based SEO
classification of research article text,
analyzing queries for spatial search Iterative query segmentation Better interaction between the
Hakimpour [34] Induces to spatial complexity
engines and spatial relationships. users and the search application
algorithm changes, enabling SEO professionals to make
IV. REVIEW OF SEO APPROACHES USING ML proactive adjustments. Overall, the use of ML in SEO offers
The prime objective of any SEO approach is to find the numerous benefits, including increased accuracy in predicting
targeted content which could meet the expectation of the user search engine algorithms, automation of SEO tasks, and the
and thereby make the web content available to them with least ability to analyze large amounts of data. This section briefs
effort. This operation demands a better for of optimization, about some of the literatures where ML approaches has
where Machine Learning (ML) approach plays a significant contributed towards this optimization process considering
contributory role. ML can help SEO professionals by analyzing various forms of use-cases.
the vast amounts of data required to optimize a website's The most recent work carried out by Boppana and Sandhya
ranking. For instance, it can be utilized to search ranking [35] have used Recurrent Neural Network (RNN) in order to
factors to get insight into website age, bounce rate, and content facilitate a better form of recommendation system to be used in
length. These were significant indicators of high-ranking SEO operation with perspective to web crawling practices. The
websites. ML can also help predict future search engine

89 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

core target of this work is mainly to reduce the error while A unique work carried out by Lister [42] has considered a
recommending the popularity of extracted information. A use-case of improving knowledge transfer using machine
clustering approach based on extracted features from learning approach. The idea of this model is to make use of all
contextual information is implemented in this process. The the essential geo-spatial information associated with
work carried out by Burgess et al. [36] address the problems educational system and use them for constructing content,
associated with security of web-contents, which is another searching relevant contents, and exploring essential knowledge
essential concern in SEO process. The authors have used Long contents. This process exponentially facilitates for SEO
Short-Term Memory (LSTM) for identifying the possible implementation over educational system. Adoption of SEO
threat in traffic associated with web-content while making towards education system is also investigated by Peralta et al.
redirection in HTTP. The study claims of successful control of [43] where a problem associated with tedious search process by
such malicious redirection. Similar aspect of security teacher in finding appropriate content is addressed. The study
consideration was also witnessed in investigation carried out has used a probability-based computational framework
by Liu and Fu et al. [37] where an SEO tool is required to followed by resource classification in the form of clusters to
confirm the vulnerability in the web-contents. The solution is make the search easier. Studies towards educational system
provided by the author by considering phishing attack on web further continues in the work of Rahman and Abdullah [44]
contents where feature learning is used. The study has used an which deals with more about customization of
unsupervised learning methodology in order to identify the recommendation system.
insecure web-contents. Further, the model has also used a
Credibility is another essential attribute to be considered
random walk of biased nature considering fusion of
during SEO operation in order to assess the source of
information over URL and structural information.
information. Such motive is seen to be implemented in work of
Soliman et al. [38] have implemented a model using Mahmood et al. [45] where reputation computation is carried
random forest for addressing the need of semantics and linked out by eliminating the negative referrals. The study has used
data of the web-contents. The implementation has used feedback-based Bayesian network in order to compute the level
Resource Description Framework (RDF) where random forest of expertise. Further, the work of Massaro et al. [46] have used
is used for retrieving the current state of RDF for assisting in neural network along with LSTM in order to assess the
further classification process. Study in the direction of the influence of web-content over an experience of user. Social
recommendation system in SEO is also reported in work of network plays a dominant role in its interactive web-content
Ismail et al. [39], where the focus is mainly towards where SEO plays a significant challenge to promote
customizing the recommendation system over web-contents. information on such platform in presence of complicated
The study model has used fuzzy logic concept integrated with connected nodes in social network. Such problem is addressed
structural analysis for achieving adaptive recommendation in Abu-Salih et al. [47] where it targets to find the social
system. Label propagation is another essential target to be influencer on the basis of domain considering both machine
achieved in SEO and it becomes quite challenging in presence learning and semantic analysis. Further study towards social
of heterogenous information. Study in such problem is network is also seen in work of Tey et al. [48] and Xu et al.
addressed by Hisano et al. [40] by storing a voluminous [49] where a recommendation system is built. The work carried
information in the form of a network followed by applying out by Serrano [50] has investigated the impact of deep
Jacobian iteration for learning weights. This technique also learning for computing the learning relevance towards
contributes towards performing better analysis. It should be searching voluminous web-content. It is to be noted that a
noted that web-contents consideration in SEO will also be structured corpora is required for building effective SEO as
inclusive of presence of multi-media file systems too. It is noted in work of Tahir et al. [51]. The work carried out by
found that identification of highlights of such files is Yuan et al. [52] have used a supervised learning approach for
completely dependent on trained data curated by human. This feature normalization in order to improvise the interaction
hinders scalability as well as is expensive in nature of process of web contents. Further work is also carried out by
deployment. This problem is addressed in work of Kim et al. Zhou et al. [53] towards user preference and recommendation
[41] by introducing a ranking mechanism using deep learning of video tags is carried out by Zhou et al. [54]. Table II
technique in presence of noise. The technique is completely highlights the summary of the work being discussed in this
free from any category as well as harnesses such web-contents section.
that are weakly supervised.

90 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

TABLE II. SUMMARY OF SEO USING ML TECHNIQUES

Authors Problems Techniques Advantage Limitation

Boppana and Error minimization during Domain specific
RNN, clustering Achieves 99.6% of accuracy
Sandhya [35] recommendation implementation
Burgess et al. [36] Malicious redirection LSTM Achieves 98.78% of accuracy Induces to spatial complexity
Induces complexity
Liu and Fu et al. Identification of insecure web- Achieves more than 95% of
Unsupervised feature learning associated with feature
[37] contents precision
matching during validation
Doesn't address prediction
Soliman et al. [38] Effective search of web-contents Random forest Achieves 92% of accuracy performance of retrieval of
data
Higher dependency towards
Ismail et al. [39] Unstructured web-contents Fuzzy Logic Achieves 94% of accuracy
ruleset
Building network with
Case specific prediction of
Hisano et al. [40] Prediction (use-case based) heterogeneous data, weight Improved accuracy
web-contents
learning
Iterative process, not
Identification for highlights of
Kim et al. [41] Deep learning using ranking Category independent applicable for active SEO
multimedia file system
tool
Helpful for knowledge delivery The model lacks adoption of
Lister [42] Adoption of knowledge contents Pedagogy-based learning
system constraints
Recommendation system
Complex search process of Better performance for hybrid No benchmarking
Peralta et al. [43] using Probability, annotation
educational content recommendation computationally
of learning resources
Rahman and Customization of educational Profile-based learning system, Effective learning outcomes on
No benchmarking
Abdullah [44] contents decision tree real-test
Mahmood et al. Applicable for smaller
Credibility analysis Bayesian network (Feedback) Good convergence performance
[45] network of web.
Intelligent score allocation of Restricted to smaller number
Massaro et al. [46] LSTM, Neural network Simplified modelling
webpage of webpages
Sentiment analysis, machine
Abu-Salih et al. Extracting contextual contents of learning, retrieval of Capable of processing larger Domain-dependent
[47] social network influencer, graphical data implementation
approach
Recommendation issue in social Not applicable for complex
Tey et al. [48] Personalized recommender Simplified structural model
network network
Model dependent on human
Personalized search and Disambiguation in
Xu et al. [49] Ontological similarity intervention towards input
recommendation recommendation design
feature
Review study towards Doesn't specifically
Investigational study towards neural Random neural network to have
Serrano [50] ranking and relevance of considered internal
network higher scope
learning models processing of SEO
Mean yield of crawling
Tahir et al. [51] Reliable corpora building Generation of corpora Specific to language
improves significantly
Optimizing interaction of web Assessed on one type of
Yuan et al. [52] Supervised learning Energy reduction
contents client application
Zhou [53] Minimize dependencies on
Evaluation of ranking performance Gain attribute learning Highly iterative scheme
labelling
Zhou [54] Recommendation (video tag) Deep learning Scalable model For smaller data

91 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

availability of competitor analyzed data as well as all

V. EXISTING SEO TOOLS the aggregated keywords [61].
At present, there are various commercially available SEO • There are also various other commercially available
tools which are meant to productively use time and effort SEO tools e.g., Screaming Frog [62], Keywords
towards performing data analysis and research. Some of the Everywhere [63], Fat Rank [64], Siteliner [65],
existing SEO tools commercially used are as follows: SEOQuake [66], Google Trends [67], Majestic [68],
A. Commercial SEO Tools Woorank [69], SpyFu [70], etc. Further, information
about the beneficial and limiting attributes of all the
• Ubersuggest: This is a free SEO tool that is meant to
discussed commercially used SEO tools are as follows:
determine the best suited keywords followed by
concluding the intention behind it. It does so by B. Beneficial Attributes Existing SEO Tools
exhibiting both the long and short phrases of top ranked The first advantage of majority of these SEO tools are that
webpage. An exclusive report is generated on the basis they are free of cost. The paid tools are based on usage
of trend analysis, degree of competition, and quantity of patterns. Majority of them are reported to use local SEO tools
keywords [55]. in order to optimize the localized traffic. They are also mobile
• Moz Pro: This SEO tool is considered as one of the best friendly as well as customer friendly while the recommendation
products by experts owing to its up-to-date services services are based on experts.
even compared to Google services with search C. Limiting Attributes Existing SEO Tools
algorithm. Various beneficial response are facilitated to
the user via its recommendation system. Apart from A robust usage of SEO will yield a page with higher rank
this, it also offers recommendation of various keywords and this will also attract the attention of competitors. Hence,
that contribute towards increasing page ranking. this is a continuous effort to be at top of rank, which is
Various web-metrics are retrieved from client extremely challenging. There are fair feasibility of SEO to
application in order to assess its performance via this change which often causes uncertainty of consistency of ranks
SEO tools [56]. in upcoming times. The process of generation of response in
SEO is quite a slower process. Even after frequent webpage
• KWFinder: The prime motive of this SEO tool is to updating, there is no assurance of timely results within a
assist in evaluating all the keywords with long trail that tentative duration of time.
has minimal competitive level. It can perform
evaluation of ranking as well as enhancement of VI. EXISTING RESEARCH TREND
specific key metric in order to upgrade popularity of At present, there are different categories of studies being
webpage [57]. undertaken for improving the performance of SEO. Table III
• SEMRush: This is one of the most frequently used highlights the research trends of using different standard
digital marketing tool which facilitates the user to verify approaches in SEO.
the ranking of their webpage. It also performs feasibility
TABLE III. SUMMARY RESEARCH TRENDS ON SEP (2017-2022)
analysis for new ranking as well as analysis among
different domain. Therefore, it offers significant Items Conference Journal Early Books Magazine
privilege to assess their services with that of Access
competitors on the basis of analytical report [58]. Article
• Google Search Console: This tool is freely available for Total 298 70 12 3 3
all users facilitated by Google. This tool can be used for manuscript
indexing the sitemap of the webpage by adding their NLP-based 2 10 0 0 0
code or via using Google Analytics. This SEO tool also approach
let the user control about the indexing policies as well ML-based 29 12 1 0 0
as it also controls the representation structure of the approach
website. Apart from this, the complete visualization and
Miscellaneous 267 48 11 3 3
usage aspect of the user can be controlled by this SEO
tools [59].
From Table III, it can be seen that there are very a smaller
• Ahrefs: This SEO tool is mainly used for online number of journal publications associated with both standard
crawling of the websites. The core purpose of its usage NLP and ML based approach in SEO as compared to
resides in finding out the backlinks used by the miscellaneous approaches, which are normally application
competitor. Further, it is also used for exploring the specific. The trend of minimal journal publication eventually
contents with highest links as well as it can also repair means that both NLP and ML approach has just very a smaller
the broken links to find out popular web-contents [60]. number of research implementation in IEEE Xplore digital
library. Similar trend of publication towards NLP and ML is
• Serpstat: This tool is used as a hacking platform for also observed for other reputed publication of Elsevier,
achieving goals of content marketing and SEO. It Springer, Wiley, etc. This concludes that there should be more
carries out all the task that is required for managing attempts towards wholesome utilization of NLP and ML
team to analyze the competitors. It also has an enriched

92 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

approach for addressing the open-end research problems as VIII. DISCUSSION AND RESEARCH IMPLICATIONS
illustrated in next section. In this survey work, the study explored the use of NLP and
VII. RESEARCH GAP ML techniques in SEO. Through the literature review, it has
been found that NLP techniques are particularly useful in
After reviewing the existing approaches towards addressing improving the readability and quality of web content, while ML
the challenges in SEO, following research gap has been techniques are effective in analyzing various factors that
identified. influence search rankings. However, a combination of both
A. More Focus on Local Problems techniques is often most effective, and there is a growing body
of research on the integration of NLP and ML in SEO. This
A closer look into the existing approaches towards SEO section delves deeper into the specific implications of these
shows that there are different variants of techniques in order to findings. The entire section includes discussing the practical
address specific set of problems or to cater up certain implications of these findings for SEO practitioners and web
application demands. However, there is no existing framework, content creators. Additionally, this section addresses challenges
which can develop a solution towards addressing combined in the current research on NLP and ML for SEO, and suggests
local problems over webpages e.g., duplicated contents, potential avenues for future research to address these issues.
difference in performance in different computing device (e.g.,
PC, tablet, Smartphone), poor link building, inaccurate A. Findings and Discussion
navigation system, not search friendly, inaccurate redirection, One of the most significant challenges in SEO is predicting
cluttered URLs, loading of page to be consuming high time, and analyzing search engine algorithms. Based on the above-
ignoring local search or not considering markup data. mentioned discussion it has been explored that, both NLP and
Although, all the above-mentioned problems have been ML techniques have been increasingly used in SEO to help
individually found to be investigated, but they have not been search engines better understand the intent and meaning of web
combinedly addressed. Solving some of the local problems and content, and to improve search rankings. One of the most
ignoring the remaining of problems will eventually lead to common applications is the use of NLP to better understand
impractical solution towards improving SEO. search queries and match them with relevant content. It can be
B. Few Emphases Towards Content Generation adopted to identify the underlying meaning and intent of search
queries, and then match them with the most relevant content on
One of the targets of the SEO approach is to generate a the web. Another way that NLP techniques can be used in SEO
precise content in order to meet the business objectives by is to improve the readability and quality of web content.
reaching to maximum targeted customer. However, this is Researchers have developed tools that use NLP to analyze the
highly computationally challenging task. Existing approaches readability, grammar, and spelling of web content, and provide
has evolved up with various techniques to ensure content suggestions for improvement. On the other hand, ML
quality, meta-data generation, and accuracy in its predictive techniques have been also be used to improve SEO in a number
approach. Such problems are mainly found to be solved using of ways. One of the most common applications is the use of
different variants of artificial intelligence and ML approaches. ML to predict search rankings. Researchers have developed
However, all such ML techniques suffer from serious algorithms that use ML to analyze various factors that
drawbacks either of computational complexities or towards influence search rankings, such as keyword density, backlinks,
dependencies toward massive trained data. Existing ML and user engagement, and then make predictions on which
approaches are also highly iterative and is mainly meant for websites are most likely to rank highly.
passive mode of predictive operation. Therefore, they are less
likely to be used for practical world application of SEO. Irrespective of various number of research-based models
being evolved, there are still an open-end problems associated
C. Few Studies Towards Smart Content Management with the performance of SEO. From commercial application
There is no doubt that ranking plays a significant role in viewpoint, existing studies don't promote towards potential
SEO building process. However, such forms of ranking links exploration while developing the model which will
mechanism suffer from lower scale of adoption of objective present the client webpage towards maximized rankings of
function. Moreover, usage of existing deep learning scheme search engine. The existing models do offer some solution to
makes the process so much complicated and resource promote the popular content based on domain specific
dependent that there is less scope of performing updating frameworks; however, there is lack of consistency towards the
procedure. Without proper updating procedure, it is impossible link building process. Irrespective of various study
to revise the solution being built for addressing local problems implementation using NLP, existing research work also doesn't
in SEO. At the same time, implementation of existing seem to consider much of content management programs along
frameworks using NLP or ML will require serious re- with considering complexities of data within it. One such issue
engineering process, which is definitely not a cost-effective is presence of iterative tags of title, which still existing NLP is
deployment scheme. not able to address properly. The content management using
NLP is required to be consistently updated, without which
Hence, all the above-mentioned research gap are required to
dynamic crawling could lead to ineffective convergence of
be bridged, without which a better form of SEO tool is
search operation of web contents. Although, existing
impractical to be designed.
contribution of ML are quite notable; but they are also scattered
as well as highly specific to use-cases. Hence, adoption of such
models will be quite expensive and will require time-to-time

93 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

update and amendment based on business structure. At present, developing a strong ecosystem of a holistic marketing. In this
there is no generalized architecture or framework to address perspective, there are evolution of massive number of searches
global problems all together. There is an increased proliferation by the customers and digital marketers annually with an
in using different variants of ML approach towards optimizing intention of fulfilling certain commercial targets. The prime
various essential operation in building an effective SEO. outcome is to end up their search towards more relevant
However, existing ML approaches are mainly iterative, conclusive services or products. For this purpose, the webpage
demands voluminous set of data, and doesn't have much is required to be optimized for maximized ranking and higher
consideration of multi-objective function along with adoption visibility. Based on above learning outcomes, potential
of practical constraints. This further reduces the scope of research gap is explored and the future work will be carried out
predictive approach and hence, existing SEO has not yet towards addressing all the pitfalls of existing system as well as
harnessed the full capabilities of ML approaches in order to adopt all the beneficial points of the existing literatures. The
gain a better result. first research gap is possible to be solved by developing a
unique architecture integrating both NLP and ML approach,
B. Remarks and Implications which will be capable to address majority of the local problems
It's difficult to determine which method is better, as both in building SEO using predictive page ranking approach. The
NLP and ML have their own strengths and weaknesses, and the second research gap can be solved by further improving the
choice of method will depend on the specific application and similar architecture and add novel functionalities towards
context. efficient content generation process in SEO. A new variant of
NLP techniques are particularly useful in understanding the deep learning approach can be used with feedback connection
natural language used in search queries and web content. They over a tree-based network system. This will offer a capability to
can help search engines better understand the intent and processes complete sequence of data available in web page.
meaning behind search queries, and can also improve the Focus will be also towards achieving better predictive
readability and quality of web content. However, NLP generated data with lesser epoch values for confirming lower
techniques may not be as effective in analyzing more computational complexities. The third research gap can be
quantitative factors, such as keyword density and backlinks, addressed by further improving the same model using
which are important for search rankings. On the other hand, improved version of machine learning algorithm. In order to
ML techniques are particularly useful in analyzing large meet an optimization objective, a multi-objective function can
amounts of data and identifying patterns that are difficult for be designed using three parameters i.e., state, reward, and
humans to detect. They can be used to analyze various factors actions in order to get more updated contents.
that influence search rankings, such as keyword density, REFERENCES
backlinks, and user engagement, and can make predictions on
[1] N. Papagiannis, Effective SEO and Content Marketing The Ultimate
which websites are most likely to rank highly. However, ML Guide for Maximizing Free Web Traffic, Wiley, ISBN: 9781119628859,
techniques may not be as effective in analyzing the natural 1119628857, 2020
language used in search queries and web content. [2] A. Veglis, D. Giomelakis, Search Engine Optimization, MDPI AG,
ISBN: 9783039368181, 3039368184, 2021
While NLP and ML techniques are often used separately in
[3] T. Kelsey, Introduction to Search Engine Optimization-A Guide for
SEO, there is also a growing body of research on the Absolute Beginners, Apress, ISBN: 9781484228517, 1484228510, 2017
integration of these techniques. In many cases, a combination
[4] L. Welz, SEO For Beginners-Explained SEO In Simple Language,
of both NLP and ML techniques may be most effective. For Beginner To Advanced: Marketing Strategies Book, Independently
example, using NLP to better understand search queries and Published, ISBN: 9798714191374, 2021
match them with relevant content, and using ML to predict [5] J. Knight, SEO For Beginners 2020-Learn and Develop a Strategy for
search rankings based on a range of factors. Additionally, the Search Engine Optimization and Grow Your Business With Google,
effectiveness of either technique will depend on the quality of Amazon Digital Services LLC - KDP Print US, ISBN: 9781670861061,
the data used and the specific algorithms and models used. 1670861066, 2019
Another area of research is the use of NLP and ML to identify [6] A. V. Patil and V. Madhukar Patil, "Search Engine Optimization
Technique Importance," 2018 IEEE Global Conference on Wireless
and address black hat SEO techniques, such as keyword Computing and Networking (GCWCN), 2018, pp. 151-154, doi:
stuffing and link farming. An algorithm can be developed using 10.1109/GCWCN.2018.8668581.
NLP and ML to detect web content that has been artificially [7] V. M. Patil and A. V. Patil, "SEO: On-Page + Off-Page Analysis," 2018
optimized for search engines and prevent websites from using International Conference on Information , Communication, Engineering
them to manipulate search rankings. and Technology (ICICET), 2018, pp. 1-3, doi:
10.1109/ICICET.2018.8533836.
Although, the use of NLP and ML in SEO offers numerous [8] A. Husayni, The Google SEO Handbook-How to Analyze and Optimize
benefits, but it also has limitations, including the accuracy of Your Site's Search Footprint Like a Pro, Millionairium, ISBN:
the algorithms used and the cost of implementing technology. 9780990782001, 099078200X, 2019
As ML and NLP technology continues to advance, it is likely [9] V. Duong, Baidu SEO-Challenges and Intricacies of Marketing in China,
that it will become increasingly essential in optimizing website Wiley, ISBN: 9781119368724, 1119368723, 2017
ranking and visibility. [10] K. Sandhu, Emerging Challenges, Solutions, and Best Practices for
Digital Enterprise Transformation, Business Science Reference, ISBN:
IX. CONCLUSION 9781799885894, 1799885895, 2021
[11] Van Looy A. "Search Engine Optimization". In: Social Media
This paper has investigated towards the performance Management. Springer Texts in Business and Economics. Springer,
improvement approaches from research viewpoint towards Cham. (2016), https://doi.org/10.1007/978-3-319-21990-5_6

94 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

[12] V. N. Gudivada, D. Rao and J. Paris, "Understanding Search-Engine [32] F. Zhang, H. Niu, I. Keivanloo and Y. Zou, "Expanding Queries for
Optimization," in Computer, vol. 48, no. 10, pp. 43-52, Oct. 2015, doi: Code Search Using Semantically Related API Class-names," in IEEE
10.1109/MC.2015.297 Transactions on Software Engineering, vol. 44, no. 11, pp. 1070-1082, 1
[13] Z. Hui, Q. Shigang, L. Jinhua and C. Jianli, "Study on Website Search Nov. 2018, doi: 10.1109/TSE.2017.2750682.
Engine Optimization," 2012 International Conference on Computer [33] E. A. Calvillo, R. Mendoza, J. Munoz, J. C. Martinez, M. Vargas and L.
Science and Service System, 2012, pp. 930-933, doi: C. Rodriguez, "Automatic algorithm to classify and locate research
10.1109/CSSS.2012.236 papers using natural language," in IEEE Latin America Transactions,
[14] Hussien, A. S. "Factors affect search engine optimization." International vol. 14, no. 3, pp. 1367-1371, March 2016, doi:
Journal of Computer Science and Network Security 14, no. 9 (2014): 28- 10.1109/TLA.2016.7459622.
33. [34] E. Hamzei and F. Hakimpour, "Entity recognition and disambiguation
[15] Persynska, K.: 8 risky black hat SEO techniques used today. Positionaly for natural-language spatial search queries," 2017 3th International
Blog (2015) Conference on Web Research (ICWR), 2017, pp. 32-37, doi:
10.1109/ICWR.2017.7959301.
[16] Agrawal, S., Somani, A., Chhabra, V.: Discernment of search engine
spamming and counter measure for it, India, 8 August 2016 [35] V. Boppana & P. Sandhya, "Web crawling based context aware
recommender system using optimized deep recurrent neural network",
[17] Killoran, John B. "How to use search engine optimization techniques to SpringerOpen-Journal of Big Data, Article No. 144, 2021
increase website visibility." IEEE Transactions on professional
communication 56, no. 1 (2013): 50-66. [36] J. Burgess, P. O'Kane, S. Sezer and D. Carlin, "LSTM RNN: detecting
exploit kits using redirection chain sequences", SpringerOpen-
[18] Hajeer, Safaa I., Rasha M. Ismail, Nagwa L. Badr, and Mohamed Fahmy Cybersecurity, Article No. 25, 2021
Tolba. "A new stemming algorithm for efficient information retrieval
systems and web search engines." In Multimedia Forensics and Security, [37] X. Liu and J. Fu, "SPWalk: Similar Property Oriented Feature Learning
pp. 117-135. Springer, Cham, 2017. for Phishing Detection," in IEEE Access, vol. 8, pp. 87031-87045, 2020,
doi: 10.1109/ACCESS.2020.2992381.
[19] Tsuei, Hung-Jia, Wei-Ho Tsai, Fu-Te Pan, and Gwo-Hshiung Tzeng.
"Improving search engine optimization (SEO) by using hybrid modified [38] H. Soliman, "Random Forest Based Searching Approach for RDF," in
MCDM models." Artificial Intelligence Review 53, no. 1 (2020): 1-16. IEEE Access, vol. 8, pp. 50367-50376, 2020, doi:
10.1109/ACCESS.2020.2980155.
[20] Luh, Cheng-Jye, Sheng-An Yang, and Ting-Li Dean Huang. "Estimating
Google's search engine ranking function from a search engine [39] H. M. Ismail, B. Belkhouche and S. Harous, "Framework for
optimization perspective." Online Information Review (2016). Personalized Content Recommendations to Support Informal Learning in
Massively Diverse Information Wikis," in IEEE Access, vol. 7, pp.
[21] Jenkins, Porter, Jennifer Zhao, Heath Vinicombe, Anant Subramanian, 172752-172773, 2019, doi: 10.1109/ACCESS.2019.2956284.
Arun Prasad, Atillia Dobi, Eileen Li, and Yunsong Guo. "Natural
language annotations for search engine optimization." In Proceedings of [40] R. Hisano, D. Sornette, and T. Mizuno, "Prediction of ESG compliance
The Web Conference 2020, pp. 2856-2862. 2020. using a heterogeneous information network", SpringerOpen-Journal of
Big Data, Article No. 22, 2020
[22] Sharma, Sunny, Sunita Mahajan, and Vijay Rana. "A semantic
framework for ecommerce search engine optimization." International [41] H. Kim, T. Mei, H. Byun and T. Yao, "Exploiting Web Images for Video
Journal of Information Technology 11, no. 1 (2019): 31-36. Highlight Detection With Triplet Deep Ranking," in IEEE Transactions
on Multimedia, vol. 20, no. 9, pp. 2415-2426, Sept. 2018, doi:
[23] Zhang, Lu, Tiantian Wang, Yiran Liu, and Qingling Duan. "A semi- 10.1109/TMM.2018.2806224.
structured information semantic annotation method for Web
pages." Neural Computing and Applications 32, no. 11 (2020): 6491- [42] P. J. Lister, "A smarter knowledge commons for smart learning",
6501. SpringerOpen-Smart Learning Environment, Article No 8, 2018
[24] F. Horasan, “Keyword extraction for search engine optimization using [43] M. Peralta, R. Alarcon, K. Pichara, T. Mery, F. Cano and J. Bozo,
latent semantic analysis,” J. Polytech., 24, no. 2: 473-479 2020. "Understanding Learning Resources Metadata for Primary and
Secondary Education," in IEEE Transactions on Learning Technologies,
[25] E. Uzun, "A Novel Web Scraping Approach Using the Additional
vol. 11, no. 4, pp. 456-467, 1 Oct.-Dec. 2018, doi:
Information Obtained From Web Pages," in IEEE Access, vol. 8, pp. 10.1109/TLT.2017.2766222.
61726-61740, 2020, doi: 10.1109/ACCESS.2020.2984503.
[44] M. M. Rahman and N. A. Abdullah, "A Personalized Group-Based
[26] D. P. Barrett, A. Barbu, N. Siddharth and J. M. Siskind, "Saying What
Recommendation Approach for Web Search in E-Learning," in IEEE
You're Looking For: Linguistics Meets Video Search," in IEEE
Access, vol. 6, pp. 34166-34178, 2018, doi:
Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no.
10.1109/ACCESS.2018.2850376.
10, pp. 2069-2081, 1 Oct. 2016, doi: 10.1109/TPAMI.2015.2505297.
[45] S. Mahmood, A. Ghani, A. Daud and S. Shamshirband, "Reputation-
[27] D. Dominguez-Sal, J. Aguilar-Saborit, M. Surdeanu and J. L. Larriba-
Based Approach Toward Web Content Credibility Analysis," in IEEE
Pey, "Using Evolutive Summary Counters for Efficient Cooperative
Access, vol. 7, pp. 139957-139969, 2019, doi:
Caching in Search Engines," in IEEE Transactions on Parallel and
10.1109/ACCESS.2019.2943747.
Distributed Systems, vol. 23, no. 4, pp. 776-784, April 2012, doi:
10.1109/TPDS.2011.162. [46] A. Massaro, D. Giannone, V. Birardi and A. M. Galiano, "An Innovative
Approach for the Evaluation of theWeb Page Impact Combining User
[28] A. Ghanbarpour and H. Naderi, "An Attribute-Specific Ranking Method
Experience and Neural Network Score", MDPI Journal, Future Internet,
Based on Language Models for Keyword Search over Graphs," in IEEE vol.12, Iss.145, 2021.https://doi.org/10.3390/fi13060145
Transactions on Knowledge and Data Engineering, vol. 32, no. 1, pp. 12-
25, 1 Jan. 2020, doi: 10.1109/TKDE.2018.2879863. [47] B. Abu‑Salih, K. Y. Chan, O. Al‑Kadi, "Time‑aware domain‑based
social influence prediction", SpringerOpen-Journal of Big Data, Article
[29] S. Soltani, S. A. H. Seno and R. Budiarto, "Developing Software No.10, 2020
Signature Search Engines Using Paragraph Vector Model: A Triage
Approach for Digital Forensics," in IEEE Access, vol. 9, pp. 55814- [48] F. J. Tey, T‑Y Wu, C‑L Lin, and J‑L Chen, "Accuracy improvements for
55832, 2021, doi: 10.1109/ACCESS.2021.3071795. cold‑start recommendation problem using indirect relations in social
networks", SpringerOpen-Journal of Big Data, vol.8, Iss.98, 2021
[30] X. Dai, H. Dai, G. Yang, X. Yi and H. Huang, "An Efficient and
Dynamic Semantic-Aware Multikeyword Ranked Search Scheme Over [49] Z. Xu, O. Tifrea-Marciuska, T. Lukasiewicz, M. V. Martinez, G. I.
Encrypted Cloud Data," in IEEE Access, vol. 7, pp. 142855-142865, Simari and C. Chen, "Lightweight Tag-Aware Personalized
2019, doi: 10.1109/ACCESS.2019.2944476. Recommendation on the Social Web Using Ontological Similarity," in
IEEE Access, vol. 6, pp. 35590-35610, 2018, doi:
[31] L. -C. Chen, "A Study of Optimizing Search Engine Results Through 10.1109/ACCESS.2018.2850762
User Interaction," in IEEE Access, vol. 8, pp. 79024-79045, 2020, doi:
10.1109/ACCESS.2020.2990972. [50] W. Serrano, "Neural Networks in Big Data and Web Search", MDPI,
data, vol.4, Iss.7, 2019.doi:10.3390/data4010007

95 | P a g e
www.ijacsa.thesai.org
 (IJACSA) International Journal of Advanced Computer Science and Applications,
Vol. 14, No. 2, 2023

[51] B. Tahir and M. A. Mehmood, "Corpulyzer: A Novel Framework for [60] "Ahrefs - SEO tools & resources to grow your search
Building Low Resource Language Corpora," in IEEE Access, vol. 9, pp. traffic," Ahrefs.com. [Online]. Available: https://ahrefs.com/. [Accessed:
8546-8563, 2021, doi: 10.1109/ACCESS.2021.3049793. 22-Nov-2022]
[52] L. Yuan, J. Ren, L. Gao, Z. Tang and Z. Wang, "Using Machine [61] "Serpstat — growth hacking tool for SEO, PPC and content
Learning to Optimize Web Interactions on Heterogeneous Mobile marketing," Serpstat.com. [Online]. Available: https://serpstat.com/.
Systems," in IEEE Access, vol. 7, pp. 139394-139408, 2019, doi: [Accessed: 22-Nov-2022].
10.1109/ACCESS.2019.2936620. [62] D. T. C. Stawart, Ed., Screaming Frog Seo Spider. Dicho, 2012.
[53] K. Zhou, H. Zha, Y. Chang and G. -R. Xue, "Learning the Gain Values [63] "Browser add-on to see Google search volume
and Discount Factors of Discounted Cumulative Gains," in IEEE everywhere," Keywordseverywhere.com. [Online]. Available:
Transactions on Knowledge and Data Engineering, vol. 26, no. 2, pp. https://keywordseverywhere.com. [Accessed: 22-Nov-2022]
391-404, Feb. 2014, doi: 10.1109/TKDE.2012.252
[64] “FatRank - digital nomad,” FatRank, 31-Jul-2017. [Online]. Available:
[54] R. Zhou, D. Xia, J. Wan and S. Zhang, "An Intelligent Video Tag https://www.fatrank.com/. [Accessed: 22-Nov-2022].
Recommendation Method for Improving Video Popularity in Mobile
Computing Environment," in IEEE Access, vol. 8, pp. 6954-6967, 2020, [65] "Siteliner - Find Duplicate Content on your site," Siteliner.com.
doi: 10.1109/ACCESS.2019.2961392. [Online]. Available: https://www.siteliner.com/. [Accessed: 22-Nov-
2022].
[55] Patel, Neil. “Ubersuggest: Free Keyword Research Tool.” Available:
https://neilpatel.com/ubersuggest. [Accessed: 21-Nov-2022] [66] A Powerful SEO Toolbox for your Browser," Seoquake.com. [Online].
Available: https://www.seoquake.com/index.html. [Accessed: 22-Nov-
[56] Moz. (n.d.). Moz Pro. Retrieved from https://moz.com/products/pro. 2022].
[Accessed: 22-Nov-2022]
[67] "Google trends," Google Trends. [Online]. Available:
[57] KWFinder. (n.d.). Keyword Research and Analysis Tool. Retrieved from https://trends.google.com/trends/?geo=IN. [Accessed: 22-Nov-2022]
https://kwfinder.com/.[Accessed: 22-Nov-2022]
[68] Majestic maps and categorizes the web," Majestic.com. [Online].
[58] Semrush - online marketing can be easy," Semrush. [Online]. Available: Available: https://majestic.com/. [Accessed: 22-Nov-2022].
https://www.semrush.com/. [Accessed: 22-Nov-2022].
[69] "Website optimization and digital agency sales tools," Woorank.com.
[59] Google Search Central (formerly Webmasters)," Google Developers. [Online]. Available: https://www.woorank.com/. [Accessed: 22-Nov-
[Online]. Available: https://developers.google.com/search. [Accessed: 2022].
22-Nov-2022]
[70] K. JFounder/CEO, "SpyFu - competitor keyword research tools for
Google ads PPC & SEO," Spyfu.com. [Online]. Available:
https://www.spyfu.com/. [Accessed: 22-Nov-2022].

96 | P a g e
www.ijacsa.thesai.org
View publication stats