Sentiment analysis also called as Opinion mining classifies various opinions in text into categories like positive, negative as well as an implicit category of neutral. The data for this classification comes from Web (reviews, blogs, social network, discussion forums etc.). This user generated content is now regarded as a true source for exploring factual and subjective information. Sentiment analysis application involves competitive and marketing analysis as well as detection of unfavorable rumors for risk management, thereby helping companies to improve customer service, enhance their products and check the vulnerability of competitors. Opinions which are classified as positive often mean profits and fame for individuals and customers but, the system unfortunately has a loop hole where fake opinions or reviews are posted to discredit some individuals or products without disclosing their true identity. The accuracy of a sentiment analysis system in principle is to find out how well it agrees with human judgment. This paper presents a survey of various Challenges, Data Store and Levels that appear in the field of sentiment analysis.

 

Published In : IJCSN Journal Volume 2, Issue 5

Date of Publication : 01 October 2013

Pages : 01 - 04

Figures : --

Tables : --

Publication Link : ijcsn.org/IJCSN-2013/2-5/IJCSN-2013-2-5-07.pdf

 

 

 

Ms. Ashwini Rao : is pursuing PhD in Computer Engineering from NMIMS University. She has done her ME (Master of Engineering) and BE (Bachelor of Engineering) degrees in Computer Science. She is currently working as a Assistant Professor in Dept. of Information Technology at Mukesh Patel School of Technology Management and Engineering, Mumbai, India. She is currently working as a research scholar in the field of Sentiment Analysis.

 

 

 

 

 

 

 

Sentiment Analysis

Opinion Holder

Web 2.0

Supervised Learning

Spammer group detection

Subjectivity Classification

Machine Learning

 

 

 

The proliferation of various micro blogging sites offers an unprecedented opportunity to create and employ theories & technologies that search and mine for sentiments. The research community has been focusing on various mining aspects but reported solutions are still far from perfect. Most business intelligence solutions based on Sentiment analysis are extremely powerful but require a base knowledge of the underlying data in order to leverage them effectively.

Feature extractions and synonym grouping remain to be very challenging. The main question that crops up is the “sentiment analysis accuracy of the current state of the art algorithms”. This question is difficult to answer as there are so many individual sub problems which do not have annotated data for benchmark testing. One point that is worth mentioning is about the applications that Sentiment analysis can be used but requires to work on data about people’s preferences which may trigger concerns about privacy violations.

Sentiment-analysis technologies allow users to consult many people who are unknown to them, but this means precisely that it is harder for users to evaluate the trustworthiness of those people they are consulting. Thus, opinion-mining systems might potentially make it easier for users to be mis-led by malicious entities, a problem on which more research can be carried on. However, the huge practical need for such opinions will keep this field of sentiment analysis vibrant and lively for years to come.

 

 

[1] Bermingham, A. and Smeaton, A. F. (2011). On using Twitter to monitor political sentiment and predict election results. In SAAIP - Sentiment Analysis where AI meets Psychology workshop at the International Joint Conference on Natural Language Pro-cessing (IJCNLP) November 13, 2011, Chiang Mai, Thailand.

[2] Phelan, O., McCarthy, K., Bennett, M., and Smyth, B. (2011). Terms of a feather: content-based news recommendation and discovery using Twitter. In Proceedings of the 33rd European conference on Advances in information retrieval, ECIR’11, pages 448– 459, Berlin, Heidelberg. Springer-Verlag.

[3] Y. Wilks and J. Bien, “Beliefs, points of view and multiple environments,”in Proceedings of the international NATO symposium on artificial and human intelligence, pp. 147–171, USA, New York, NY: Elsevier North-Holland, Inc.,1984.

[4] Pang, B., Lee, L., and Vaithyanathan.S. Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2002, (EMNLP):79–86.

[5] Pang B. and Lee L. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales, Proceedings of the Association for Computational Linguistics (ACL),2005:115–124.

[6] Yu H. and Hatzivassiloglou V., Towards answering opinion questions: Separating facts from opinions and identifying the polarity of opinion sentences.In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2003.

[7] Turney P. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In Proceedings of the Association for Computational Linguistics (ACL), 2005: 417–424.

[8] Liu, B., Hu, M., & Cheng, J. Opinion observer: Analyzing and comparing opinions on the web. In Proceedings of the 14th international World Wide Web conference (WWW-2005). ACM Press: 10–14.

[9] Wilson T., Wiebe J., and Hoffmann P.,Recognizing contextual polarity in phrase-level sentiment analysis. In Proceedings of the Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP)2005: 347– 354.

[10] Esuli, A., & Sebastiani, F. Determining the semantic orientation of terms through gloss classification.In Proceedings of CIKM-05, the ACM SIGIR conference on information and knowledge management, Bremen, DE, 2005.

[11] Aue, A. and Gamon, M., Customizing sentiment classifiers to new domains: A case study. Proceedings of Recent Advances in Natural Language Processing (RANLP),2005.

[12] Kim, S. and Hovy, E., Determining the sentiment of opinions.In Proceedings of the International Conference on Computational Linguistics (COLING) ,2004.

[13] Kamps, J., Marx, M., Mokken, R.J., de Rijke, M., Using WordNet to measure semantic orientation of adjectives. In Language Resources and Evaluation (LREC), 2004.

[14] Hatzivassiloglou, V. and McKeown, K., Predicting the semantic orientation of adjectives. In Proceedings of the Joint ACL/EACL Conference,2004: 174–181

[15] Khairullah Khan, Baharum B. Baharudin, Aurangzeb Khan, and Fazal_e_Malik, “Automatic Extraction of Features and Opinion Oriented Sentences from Customer Reviews”, World Academy of Science, Engineering and Technology 62 2010.

[16] Pingdom (2010). Twitter, now 2 billion tweets per month. http://royal.pingdom.com/2010/06/08/twitter-now-2- billion-tweets-per-month/.

[17] Yongyong Zhail, Yanxiang Chenl, Xuegang Hu, “Extracting Opinion Features in Sentiment Patterns” , International Conference on Information, Networking and Automation (ICINA),2010.