Sentiment analysis or opinion mining is the computational study of peoples opinions, appraisals, attitudes, and emotions toward entities, individuals, issues, events, topics and their attributes. Businesses always want to find public or consumer opinions about their products and services. Potential customers also want to know the opinions of existing users before they use a service or purchase a product. With the explosive growth of social media (i.e., reviews, forum discussions, blogs and social networks) on the Web, individuals and organizations are increasingly using public opinions in these media for their decision making. However, finding and monitoring opinion sites on the Web and distilling the information contained in them remains a formidable task because of the proliferation of diverse sites. Motivation The exponential increase in the Internet usage and exchange of users opinion is the motivation for Opinion Mining. As the number of reviews that a product receives may grow rapidl y and many times the reviews may also be quite lengthy, it is hard for the customers to analyze them through manual reading to make an informed decision to purchase a product. A large number of reviews for a single product may also make it harder for individuals to evaluate the true underlying quality of a product. In these cases, customers may naturally gravitate to read a few reviews in order to form a decision regarding the product and he/ she may get only a biased view of the product. Similarly, manufacturers want to read the reviews to identify what elements of a product affect sales most, and a large number of reviews make it hard for product manufacturers or business organizations to keep track of customer's opinions and sentiments on their products and services. Since, most of the reviews are stored either in unstructured or semi-structured format; the distillation of knowledge from this huge repository becomes a challenging task. It would be a great help for both customers and manufacturers if the reviews could be processed automatically and presented in a summarized form highlighting the product features and users opinions expressed over them.. Objectives Most of the opinion mining tools classify the reviews as positive or negative. Fails to reveal the product features opinion as liked or disliked by the users. And more over the issue with all the sentimental analysers is that the parser are trained to deal with grammatically correct language. And the reviews that are obtain from sites, does not always have grammatically correct language. They general contain abbreviations, slang words, short codes etc which makes the job of the parser difficult. Methodology
The figure shows steps for analysing the sentiment of product reviews. A web crawler would extract the information from the website whose reviews have to be analysed. Resulting in HTML tags, Text and Links. In the next phase of Data preparation, filtering of noisy data takes place. Noisy data like stop for unwanted stop-words and words not listed in the dictionary. And also the HTML tags are discarded. So after the data preparation stage, only the text ie the review is retained. The pre-processed data is now classified as Informal and Formal Text. Before this data is sent for review classification the text is substituted by the equivalent formal text. Later the data is passed on to the NLP parser for classification into POS tags. Thus the feature and its accompanying opinion is identified and extracted. Continuing with the summarization stage. Thus the feature and its accompanying opinion is identified and extracted. The parsers cannot classify informal text, summarizing with informal text would informal result in ineffective summarization. To list down the steps of mining, 1. Review Documents Retrieval: For a target review site, the crawler retrieves review documents and stores them locally after filtering markup language tags. 2. Document Pre-processor: The filtered review documents are divided into manageable record-size chunks. Pre processing is done on review documents to filter out noisy reviews.
3. Document Parser: The functionality of this module is to facilitate the linguistic and semantic analysis of text for information component extraction. This module accepts record-size chunks generated by document pre-processor as input to assign Parts Of-Speech (POS) tags to each word. It also converts each sentence into a set of dependency relations between the pair of words. For POS analysis and dependency relation generation purpose, Stanford parser is used. 4. Feature Pruning and onion identification: Noun phrases generally correspond to product features, adjectives refer to opinions and adverbs are generally used as modifiers to represent the degree of expressiveness of opinions. In this system POS based filtering mechanism to avoid unwanted texts from further processing. 5. Opinion Classification and Summarization: After feature and opinion have been identified, classification of features is done to summarize (i.e., positive or negative) References 1. A.Kamal, M. Abulaish and T. Anwar, Mining Feature-Opinion Pairs and Their Reliability Scores from Web Opinion Sources, Proc 2nd Intl. Conference on Web Intelligence, Mining and Semantic, 2012. 2. Bing Liu. Sentiment Analysis and Opinion Mining, Morgan & Claypool Publishers, May 2012. 3. C. C. Aggarwal and C. Zhai, editors, Mining TextData. Springer, 2012. 4. Feldman, R., Techniques and applications for sentiment analysis, Communications of the ACM, Vol. 56 Issue 4, (2013), 82-89. 5. Lee, Dongjoo, Ok-Ran Jeong, and Sang-goo Lee. "Opinion mining of customer feedback data on the web." Proceedings of the 2nd international conference on Ubiquitous information management and communication. ACM, 2008. 6. Liddy, Elizabeth D. "Natural language processing." (2001). 7. Marie-Catherine, De Marneffe and Christopher D. Manning. "Stanford typed dependencies manual." (2008). 8. Mohammad Sadegh Hajmohammadi , Roliana Ibrahim , Zulaiha Ali Othman Opinion Mining and Sentiment Analysis: A Survey, International Journal of Computers & Technology,Volume 2 No. 3, June, 2012 . 9. Pang, B. and Lee, L. (2008). Opinion mining and sentiment analysis. Foundation andTrends in Information Retrieval, 2(1-2):1135. 10. Sheikha, Fadi Abu, and Diana Inkpen. "Learning to classif y documents according to formal and informal style." Linguistic Issues in Language Technology 8 (2012).
Software Asset Management: What Is It and Why Do I Need It?: A Textbook on the Fundamentals in Software License Compliance, Audit Risks, Optimizing Software License ROI, Business Practices and Life Cycle Management
