1.pptx

1.pptx

• 1.
  Sentiment Analysis ofProduct- Based Reviews Using Machine Learning SUPERVISOR & COORDINATOR DrVLoganathan M.E., Ph.D., Professor Computer Science and Engineering BATCH MEMBERS N Rakesh Mamila Harish Ganesh S (212219040117) (212219040071) (212219040032)
• 2.
  OBJECTIVE • Scrapping productreviews on various websites featuring various products specifically amazon.com. • Analyze sentiment on dataset from document level (review level). • Analyze and categorize review data.
• 3.
  LITERATURE SURVEY S.N O TITLE OF THE PROJECT AUTHOR NAME JOURNALMETHOD AND DESCRIPTION DRAWBACKS YEA R 1. Opinion Mining and sentiment Classificat ion S Chandrakala and C Sindhu A Survey vol:3 Survey on human opinion and identifying their sentiment using Naïve Bayesian Classifier It is not applicable for different opinions 2012 2. An analysis on opinion Mining Techniques and Tools G Angulakshmi and Dr R Manicka Opinion Mining Journal Using random forest , support vector machine and various techniques and tools. They have only initialized the problem. 2014
• 4.
  ISSUES IN EXISTINGSYSTEMS Issue 1 Issue 2 Issue 3
• 5.
  Possible solutions 1. Solution1 2. Solution 2 3. Solution 3
• 6.
  PROBLEM DEFINITION  Toclassify the Sentiment Analysis of Prodect Based Reviews, which is implemented using Machine Learning.  Sentiment analysis of product reviews has recently become very popular in text mining and computational linguistics research.  Firstly, evaluative terms expressing opinions must be extracted from the review.  Secondly, the SO, or the polarity, of the opinions must be determined.  Thirdly, the opinion strength, or the intensity, of an opinion should also be determined.  Finally, the review is classified with respect to sentiment classes, such as Positive and Negative, based on the SO of the opinions it contains.
• 7.
  PROPOSED SYSTEM Deals withtext analysis to systematically identify, extract, quantify, and study affective states and subjective information. The various classification models which are selected for categorization: Naïve Bayesian, Random Forest, Logistic Regression and Support Vector Machine. Categorization or classification of opinion sentiment into- Positive Negative
• 8.
  ARCHITECTURE DIAGRAM
• 9.
  LIST OF MODULES NaïveBayesian Classifier(NBC) Random Forest(RF) Support Vector Machine(SVM) Logistic Regression(LR)
• 10.
  SYSTEM REQUIREMENTS Hardware Requirements: Corei5/i7 processor At least 8GB RAM At least 6 GB of Usable Hard Disk Space Software Requirements: Anaconda Distribution Python 3.x UNIX/LINUX Operating System NLTK Toolkit. Data Set Information: The Amazon reviews dataset consists of reviews from amazon. The data span a period of 18 years, including ~35 million reviews up to March 2013.
• 11.
  REFERENCES [1] S. ChandraKala1and C. Sindhu2, “OPINION MINING AND SENTIMENT CLASSIFICATION: A SURVEY,”.Vol .3(1),Oct 2012,420-427. [2] G Angulakshmi , Dr R ManickaChezian ,”An Analysis on Opinion Mining: Techniques and Tools”. Vol 3(7), 2014 www.iarcce.com. [3] Zhu, Jingbo, et al. "Aspect-based opinion polling from customer reviews." IEEE Transactions on Affective Computing, Volume 2.1,pp.37-49, 2011. [4] Nasukawa, Tetsuya, and Jeonghee Yi. "Sentiment analysis: Capturing favorability using natural language processing." In Proceedings of the 2nd international conference on Knowledge capture, ACM, pp. 70-77, 2003 [5] Li, Shoushan, Zhongqing Wang, Sophia Yat Mei Lee, and Chu-Ren Huang. "Sentiment Classification with Polarity Shifting Detection." In Asian Language Processing (IALP), 2013 International Conference on, pp. 129-132. IEEE, 2013.
• 12.
  THANK YOU