Social media data analysis
Download as PPTX, PDF1 like209 views
The document discusses the significance and methods of social media data analytics, highlighting its role in understanding customer behavior, improving business strategies, and visualizing complex data sets. It outlines various types of social media data, visualization techniques, and tools like Tableau for effective analysis. Additionally, it presents a structured six-step process for social media analytics, emphasizing the importance of cleaning, analyzing, and interpreting data to derive actionable insights.
Social media data analysis
- 1. SOCIAL MEDIA DATA ANALYTICS USING VISUALIZATION Presented by Shweta Patnaik
- 2. Content • Abstract • Introduction • Data Visualization • Different type of charts • Social Media Data • Social Media Data Analytics • Tableau • Conclusion
- 3. Abstract • In the current era social media become an important part of our life. • It plays a crucial role in business, government communities, health care and many more. • People use social media in the form of real time, interactive communications made available through blogs, tweets, updates, images and videos. • There is an opportunity to analyze those social media data to improve the accuracy and scalability. Many challenges will come ahead in the development. • This paper will discuss the work of visualization, analysis methods and the result.
- 4. Introduction • Social media analytics is the practice of gathering data from social media websites and analyzing that data using social media analytics tools to make business decisions. • This is all about collecting data produced from Social Media platforms like Facebook, Twitter, LinkedIn, WhatsApp, Wikipedia, YouTube, Pinterest, Instagram, Tumblr, Snapchat, Google+, WeChat, and many others. • The data are in the form of comments, tweets, posts, likes, shares and links, geographical data, microblogs for fetching the information from the dataset using social media analytics, to make the right business decisions. • It also includes development and calculation tools and frameworks which collect, monitor, analyze, summarize, and visualize social media data.
- 5. • It is also used for learning customer sentiment and behavior and is also useful to get the insights on product reviews and data for creating better marketing strategies and improved customer service. • The general approach for social media analytics starts by identifying the credible and mineable source of information form the diverse social media platforms used for Microblogging, Blogging, Community-based Question Answering (CQA), Chats, Forums, Media Sharing, and Hybrid Applications which generate huge volumes of noisy, distributed, unstructured and dynamic data. • Sentiment analysis states to the use of natural language processing (NLP), text analytics, computational linguistics, and biometrics in identifying, extracting, quantifying and studying the affective states and subjective information to capture the emotion of the speaker or writer.
- 6. Social Media Analytics for • Social Media is a web and mobile based Internet applications that allows access and exchange of user generated contents. • Capturing user data to understand attitudes, opinions and trends, and manage online reputation. • Predicting customer behavior and improve customer satisfaction by anticipating customer needs and recommending next best actions. • Creating customized campaigns that resonate with social media participants. • Identifying the primary influencers within specific social network channels
- 7. Data Visualization • It is a term that describes any effort to help people understand the significance of data by playing it in a visual context. • To show visualized data, we use different charts (bar chart, pie chart, line chart) ,patterns, graphs…etc. • By using charts or graphs visualizing large amount of data is easier than transferring them to spreadsheets. • It can also identify areas that needs attention or improvement, simplify the factors that influence customer behavior, helps us to understand which products to place where, predict sales volumes.
- 9. Use of data visualization • Comprehend information quickly • Identify relationships and patterns • Pinpoint emerging trends • Communicate the story to others • Identify areas that need attention or improvement. • Clarify which factors influence customer behavior. • Help you understand which products to place where.
- 10. Different visualization tools • Data visualization is about how to present your data, to the right people, at the right time, in order to enable them to gain insights most effectively. • Data visualization tools have been important in democratizing data and analytics and making data-driven insights available to workers throughout an organization. • There are different data visualization tools available. Some of them are : • Tableau • Qlik • SAP Lumira • SAS visual analytics • Oracle visual analyzer
- 11. Visualization using Tableau • Tableau is an interactive data visualization tools that enables you to create interactive and apt visualizations in form of dashboards, worksheets to gain business insights for the better development of your company. • Tableau is easy to use as it focuses mainly on useful data and is a user- friendly tool. • Tableau have different products like • Tableau Desktop • Tableau Server • Tableau Online
- 12. Data source in Tableau
- 13. Social Media Data • Social media data defines all of the raw information collected from individual social media activity. • Social media data tracks how individuals engage with your content or channels like LinkedIn, Facebook, and Twitter. It gathers numbers, percentages, and statistics from which you can infer the performance of your social media strategy.
- 14. • With the social media analytics, we can answer number of questions about the success of your social media activities, such as: • Which networks contribute the most to lead generation? • What types of content makes audiences click, share, and convert? • What are my top-converting posts?
- 15. How to collect Social Media Data • Social media data is more than likes and shares. • There are different strategy to capture the data • Capturing semantically driven data • Capturing user driven data • There are different types of social media data. They are • Performance data • Conversation data • Industry or Topic data • Traffic and Link data • Conversion or result data • Referral data • Local data • Intentional data
- 16. How to control Social Media Data • Break free from rigid demographics • Build long-term relationships with customers • Predict future customer behaviors • Test marketing campaigns before launch • Make data-driven decisions
- 17. Social Media Data analytics • Social Media Analytics deals with development and evaluation of tools and frameworks to collect, monitor, analyze, summarize, and visualize social media data. • Social media analytics research serves several purposes: • Facilitating conversations and interaction between online communities and • Extracting useful patterns and intelligence to serve entities that include, but are not limited to, active contributors in ongoing dialogues. •
- 18. • Social media analytics have four different forms, such as, • Descriptive analytics • Diagnostic analytics • Predictive analytics • Prescriptive analytics
- 19. Social Media Analytics Process
- 20. • Capture : • This means define your specific social objective and KPI’s. KPI objectives should be measurable. • For example, in the review we took data from Facebook and Instagram of different pages. So, the possible KPIs will be no. of posts of the page, audience of the page, likes, trusted judgement etc. • The capture stage must balance the need for finding information from all quarters (inclusivity) with focusing on sources that are most relevant and authoritative (exclusivity) to assist in more refined understanding
- 21. • Understand : • This means define your specific social objective and KPI’s. KPI objectives should be measurable. • For example, in the review we took data from Facebook and Instagram of different pages. So, the possible KPIs will be no. of posts of the page, audience of the page, likes, trusted judgement etc. • The understand stage is the core of the entire social media analytics process. The success of this stage will have significant impact on the information and metrics that are displayed in the present stage, and thus the success of future decisions or actions that might be taken by a firm.
- 22. • Present : • After complete understanding, we need to visualize and present the same. For visualization there are different tools available. In this review we have used Tableau. • The last stage in the social media analytics process is the present stage. The results from different analytics will be summarized, evaluated, and shown to users in an easy to understand format.
- 23. • G. F. Khan, suggest that social media analytics is a six steps iterative process (involving both the science and art) of mining the desired business insights from social media data: • Step 1 Identification: Searching and identifying the right source of information for analytical purposes. • • Step 2 Extraction: Once a reliable and mineable source of social media data are identified, next comes extraction of the data through APIs or manually. • Step 3 Cleaning: This step involves removing the unwanted data from the automatically extracted data
- 24. • Step 4 Analyzing: Next, the clean data is analyzed for business insights. Depending on the layer of social media analytics under consideration and the tools and algorithm employed, the steps and approach to take will greatly vary. • Step 5 Visualization: Depending on the type of data, the analysis part will lead to relevant visualizations for effective communication of results. • Step 6 Interpretation or Consumption: This step relies on human judgments to interpret valuable knowledge from the visual data. Meaningful interpretation is of particular importance when we are dealing with descriptive analytics that leaves room for different interpretations
- 25. • This project is based on social media analytics, where the social media data has been analyzed i.e. different pages on both Facebook and Instagram. These pages are analyzed based on different KPIs (Key Performance Indicators). A huge dataset has been collected from these pages by their procedures. • The data set looks like:
- 27. Data Cleaning • Before analyzing this massive dataset, it need to be cleaned. As we know that, social media dataset holds unstructured data. These datasets consist of audio, video, images and text data as well. Not only these things but also likes, click views, page rates, comments, shares and replies are present. It may hold redundant data or kind of garbage. • Unstructured textual data are very noisy. Hence, data cleaning is an important area in social media analytics. The process of data cleaning may involve removing typographical errors or validating and correcting values against a known list of entities. • Specifically, text may contain misspelled words, quotations, program codes, extra spaces, extra line breaks, special characters, foreign words, etc.
- 29. Data Analysis • Data analytics (DA) is the process of examining data sets in order to draw conclusions about the information they contain, increasingly with the help of specialized systems and software. • Data analysis is a proven way for organizations and enterprises to gain the information they need to make better decisions, serve their customers, and increase productivity and revenue. • The benefits of data analysis are almost too numerous to count, and some of the most rewarding benefits include getting the right information for your business, getting more value out of IT departments, creating more effective marketing campaigns, gaining a better understanding of customers, and so on.
- 30. Tableau • Tableau is a top data visualization tool. It has many required and unique features. Its data discovery, exploration and visualization application allow user to answer business questions. • There is no need of any complex scripting. Anyone who understands the business problems can work with a visualization of the relevant data. After analyzing all the data in dataset, we came to a known about the ratings and the popularity of the pages in the social media.
- 31. Tableau Filters • Tableau filter is a process to remove certain values or range of values from a result set. • This feature allows both simple situations using field values as well as advanced calculation or context-based filters. • There are three types of basic filters available in Tableau such as • Filter Dimensions • Filter Measures • Filter Dates.
- 33. Tableau Worksheet • Worksheet is the area where you create the views for data analysis. • Tableau provides three blank worksheets when you have established a connection to data source, inbuilt. You can go on adding multiple worksheets to look at different data views in the same screen, one after another. • A worksheet contains a single view with shelves, cards, legends and the data and the analytics panes in its side bars. • We can create, open, duplicate, hide and delete the worksheet. Collection of worksheets is called as workbook.
- 35. Tableau Dashboard • A dashboard is a merged display of many worksheets and related information in a single place. • It is used to compare and monitor a variety of data simultaneously. • Dashboards are placed at the bottom of the workbook and they get updated with the most recent data from the data source. • A good dashboard informs with an informative look. A great dashboard combines high performance and ease of use. • So that, anybody can get the data-driven answers to their business questions. • Creating a dashboard with Tableau helps to the non-technical users to create interactive, real-time visualizations
- 37. Conclusion • Social media data has countless information and knowledge in it. It has a vast amount of noisy, unstructured, semi-structured, geographical, microblogs and dynamic data. Social media analytics is highly essential for organizations, business institutions and modern researchers to fetch capable results by developing areas like Bigdata Analytics, Data Science, Visualization and others. • This thesis will give you an overview various phases involved in social media analytics, and knowledge about most of the open source tools useful for researchers and analysts while there a numerous branded tool for more complicated and real time analytics. • In this project, a huge amount of social media data (i.e. pages on both Instagram and Facebook) has been analyzed to know their popularity, so that they can take a better future decision.
- 38. Bibliography • Wikipedia contributors. "Sentiment analysis." Wikipedia, The Free Encyclopedia. Wikipedia, The Free Encyclopedia, 24 Nov. 2017. Web. 9 Dec. 2017. • Ralph K. Yeh; Visualization Techniques for Data Mining in Business Context:A Comparative Analysis; University of Texas at Arlington • 1Anita Kumari Singh; 2 Mogalla Shashi: Research Aids for Social Media Analytics: 1.Research Scholar, Department of Computer Science & Systems Engineering, Andhra University, Visakhapatnam, India, 2. Professor, Department of Computer Science & Systems Engineering, Andhra University, Visakhapatnam, India. • https://www.sas.com/en_us/insights/big-data/data-visualization.html • https://analyticsindiamag.com/10-data-visualization-tools-industry-relies/ • https://www.tableau.com/products#oPmzrJMtAscTtzfy.99 • https://www.oktopost.com/blog/social-media-data/ • Daniel Zeng 1, Hsingchin Chen2 and Robert Lusch 3, Shu-Hsing Li 4; Social Media Analytics and Intelligence; Chinese Academy of Sciences and University of Arizona1, University of Arizona2,3, National Taiwan University4.
- 39. THANK YOU