Evaluating Potential Improvements of Collaborative Filtering with Opinion Mining

Manuela Angioni, Maria Laura Clemente, Franco Tuveri

2015

Abstract

An integration of an Opinion Mining approach with a Collaborative Filtering algorithm has been applied to the Yelp dataset to improve the predictions through the information provided by the user-generated textual reviews. The research, still in progress, based the Opinion Mining approach on the syntactic analysis of textual reviews and on a beginning polarity evaluation of the sentences. The predictions produced in this way was blended with the predictions coming from a Biased Matrix Factorization algorithm obtaining interesting results in terms of Root Mean Squared Error (RMSE), with potential enhancements. We intend to improve these results in a further phase of activity by including in the Opinion Mining approach the semantic disambiguation and by using better criteria of evaluation of the reviews taking into account a set of 12 business aspects. The Opinion Mining approach will be evaluated comparing the output in terms of predictions with the values manually assigned by a small group of people to a sample of the same reviews.

References

  1. Agerri, R., Garcia-Serrano A., 2010. Q-WordNet: Extracting polarity from WordNet senses. In LREC 2010, 7th International Conference on Language Resources and Evaluation, Malta.
  2. Angioni, M., Demontis, R., Tuveri, F., 2008, A Semantic Approach for Resource Cataloguing and Query Resolution. Communications of SIWN. Special Issue on Distributed Agent-based Retrieval Tools.
  3. Angioni, M., Tuveri F., 2011, A Semantic Approach to the Extraction of Feature Terms. ICSOFT 2011, 6th International Conference on Software and Data Technologies. SciTePress.
  4. Benamara, F., Cesarano, C., Picariello, A., Reforgiato, D., Venkatramana S. Subrahmanian, 2007. Sentiment Analysis: Adjectives and Adverbs are better than Adjectives Alone. Proceedings of ICWSM 07, International Conference on Weblogs and Social Media, pp. 203-206.
  5. Ding, X., Liu, B., Yu, P.S., 2008, A Holistic LexiconBased Approach to Opinion Mining. WSDM 7808 Proceedings of the international conference on Web search and web data mining, ACM New York, USA.
  6. Esuli, A., Sebastiani, F., 2006, SentiWordNet: A Publicly Available Lexical Resource for Opinion Mining. In Proceedings of the 5th Conference on Language Resources and Evaluation (LREC'06), p. 417-422, Genova, Italy.
  7. Fan, Mingming; Khademi, Maryam, 2014. Predicting a Business Star in Yelp from Its Reviews Text Alone. ArXiv e-prints: 1401.0864.
  8. Govindarajan, M., 2014, Sentiment Analysis of Restaurant Reviews Using Hybrid Classification Method, International Journal of Soft Computing and Artificial Intelligence, Vol. 2, Issue 1.
  9. Jahrer, M., Töscher, A., Legenstein, R., 2010, Combining Predictions for Accurate Recommender Systems, Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 693-702, ACM, 2010.
  10. Koren, Y., Bell, R., Volinsky, C., 2009, Matrix Factorization Techniques for Recommender Systems, Computer, IEEE Computer Society, v. 42, n. 8.
  11. Koukourikos, A., Stoisis, G., Karampiperis, P., 2012. Sentiment Analysis: A tool for Rating Attribution to Content in Recommender Systems. Presented at the 2nd Workshop on Recommender Systems for Technology Enhances Learning (RecSysTEL 2012), 18-19/09/2012, Saarbrucken, Germany.
  12. Levi, A., Mokryn, O., Diot, C., Taft, N., 2012. Finding a needle in a haystack of reviews: cold start contextbased hotel recommender system. In Proceedings of the sixth ACM conference on Recommender systems, pages 115-122. ACM, 2012.
  13. Magnini, B., Strapparava, C., 2004, User Modelling for News Web Sites with Word Sense Based Techniques. User Modeling and User-Adapted Interaction 14(2), pp. 239-257.
  14. Magnini, B., Strapparava, C., Pezzulo, G., Gliozzo, A., 2002. The Role of Domain Information in Word Sense Disambiguation. Natural Language Engineering, special issue on Word Sense Disambiguation, 8(4), pp. 359-373, Cambridge University Press.
  15. Miller, G., 1998. WordNet: An Electronic Lexical Database, Bradford Books.
  16. Quadrana, M., 2013. E-tourism recommender systems http://hdl.handle.net/10589/84901.
  17. Schmid, H., 1994. Probabilistic Part-of-Speech Tagging Using Decision Trees. In Proceedings of the International Conference on New Methods in Language Processing, pp. 44-49.
  18. Tosher, A., Jahrer, M., Bell, R. M., 2009, The BigChaos solution to the Netflix grand prize, Netflix Prize Documentation.
  19. Trevisiol, M., Chiarandini, L., Baeza-Yates, R., 2014, Buon Appetito - Recommending Personalized menus.
  20. Tuveri, F., Angioni, M., 2012. A Linguistic Approach to Feature Extraction Based on a Lexical Database of the Properties of Adjectives and Adverbs, Global WordNet Conference (GWC2012), Matsue, Japan.
Download


Paper Citation


in Harvard Style

Angioni M., Laura Clemente M. and Tuveri F. (2015). Evaluating Potential Improvements of Collaborative Filtering with Opinion Mining . In Proceedings of the 17th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-097-0, pages 656-661. DOI: 10.5220/0005456006560661


in Bibtex Style

@conference{iceis15,
author={Manuela Angioni and Maria Laura Clemente and Franco Tuveri},
title={Evaluating Potential Improvements of Collaborative Filtering with Opinion Mining},
booktitle={Proceedings of the 17th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2015},
pages={656-661},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005456006560661},
isbn={978-989-758-097-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 17th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - Evaluating Potential Improvements of Collaborative Filtering with Opinion Mining
SN - 978-989-758-097-0
AU - Angioni M.
AU - Laura Clemente M.
AU - Tuveri F.
PY - 2015
SP - 656
EP - 661
DO - 10.5220/0005456006560661