Opinions matter: a general approach to user profile modeling for contextual suggestion

Abstract The increasing use of mobile devices enables an information retrieval (IR) system to capitalize on various types of contexts (e.g., temporal and geographical information) about its users. Combined with the user preference history recorded in the system, a better understanding of users’ information need can be achieved and it thus leads to improved user satisfaction. More importantly, such a system could proactively recommend suggestions based on the contexts. User profiling is essential in contextual suggestion. However, given most users’ observed behaviors are sparse and their preferences are latent in an IR system, constructing accurate user profiles is generally difficult. In this paper, we focus on location-based contextual suggestion and propose to leverage users’ opinions to construct the profiles. Instead of simply recording “what places a user likes or dislikes” in the past (i.e., description-based profile), we want to construct a profile to identify “why a user likes or dislikes a place” so as to better predict whether the user would like a new candidate suggestion of place. By assuming users would like or dislike a place with similar reasons, we construct the opinion-based user profile in a collaborative way: opinions from the other users are leveraged to estimate a profile for the target user. Candidate suggestions are represented in the same fashion and ranked based on their similarities with respect to the user profiles. Moreover, we also develop a novel summary generation method that utilizes the opinion-based user profiles to generate personalized and high-quality summaries for the suggestions. Experiments are conducted over three standard TREC contextual suggestion collections and a Yelp data set. Extensive experiment comparisons confirm that the proposed opinion-based user modeling outperforms the existing description-based methods. In particular, the systems developed based on the proposed methods have been ranked as top 1 in both TREC 2013 and 2014 contextual suggestion tracks.

[1]  Christopher J. C. Burges,et al.  From RankNet to LambdaRank to LambdaMART: An Overview , 2010 .

[2]  Hua Li,et al.  User Modeling for Contextual Suggestion , 2014, TREC.

[3]  Nuria Oliver,et al.  Leveraging user comments for aesthetic aware image search reranking , 2012, WWW.

[4]  Craig MacDonald,et al.  University of Glasgow at TREC 2014: Experiments with Terrier in Contextual Suggestion, Temporal Summarisation and Web Tracks , 2014, TREC.

[5]  Mandar Mitra,et al.  A Simple Context Dependent Suggestion System , 2013, TREC.

[6]  Taghi M. Khoshgoftaar,et al.  A Survey of Collaborative Filtering Techniques , 2009, Adv. Artif. Intell..

[7]  Hui Fang,et al.  Exploration of Opinion-aware Approach to Contextual Suggestion , 2014, TREC.

[8]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[9]  Ani Nenkova,et al.  Automatic Summarization , 2011, ACL.

[10]  Yiu-Kai Ng,et al.  Predicting the ratings of multimedia items for making personalized recommendations , 2012, SIGIR '12.

[11]  Grace Hui Yang,et al.  (Not Too) Personalized Learning to Rank for Contextual Suggestion , 2012, TREC.

[12]  Daqing He,et al.  PITT at TREC 2013 Contextual Suggestion Track , 2013, TREC.

[13]  Bing Liu,et al.  The utility of linguistic rules in opinion mining , 2007, SIGIR.

[14]  Charles L. A. Clarke,et al.  Overview of the TREC 2012 Contextual Suggestion Track , 2013, TREC.

[15]  Iryna Gurevych,et al.  Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations , 2009, TSA@CIKM.

[16]  Cecilia Mascolo,et al.  A Random Walk around the City: New Venue Recommendation in Location-Based Social Networks , 2012, 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing.

[17]  Olivier Chapelle,et al.  Expected reciprocal rank for graded relevance , 2009, CIKM.

[18]  Hui Fang,et al.  Opinion-based User Profile Modeling for Contextual Suggestions , 2013, ICTIR.

[19]  James P. Callan,et al.  Modelling Psychological Needs for User-dependent Contextual Suggestion , 2014, TREC.

[20]  Lipika Dey,et al.  Opinion mining from noisy text data , 2008, AND '08.

[21]  Christophe Diot,et al.  Finding a needle in a haystack of reviews: cold start context-based hotel recommender system , 2012, RecSys.

[22]  Andrea Esuli,et al.  Automatic generation of lexical resources for opinion mining: models, algorithms and applications , 2010, SIGF.

[23]  Dipanjan Das Andr,et al.  A Survey on Automatic Text Summarization , 2007 .

[24]  Patrick Paroubek,et al.  Twitter as a Corpus for Sentiment Analysis and Opinion Mining , 2010, LREC.

[25]  Jiawei Han,et al.  Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions , 2010, COLING.

[26]  Mark T. Maybury,et al.  Automatic Summarization , 2002, Computational Linguistics.

[27]  Bamshad Mobasher,et al.  Context-Aware Recommendation Based On Review Mining , 2011, ITWP@IJCAI.

[28]  David M. Pennock,et al.  Categories and Subject Descriptors , 2001 .

[29]  Tie-Yan Liu,et al.  Learning to rank for information retrieval , 2009, SIGIR.

[30]  James Allan,et al.  Frontiers, challenges, and opportunities for information retrieval: Report from SWIRL 2012 the second strategic workshop on information retrieval in Lorne , 2012, SIGF.

[31]  Hsinchun Chen,et al.  AI and Opinion Mining , 2010, IEEE Intelligent Systems.

[32]  Dragomir R. Radev,et al.  Introduction to the Special Issue on Summarization , 2002, CL.

[33]  Guillaume Cabanac,et al.  IRIT at TREC 2012 Contextual Suggestion Track , 2012, TREC.

[34]  Hanchen Li,et al.  BJUT at TREC 2014 Contextual Suggestion Track: Hybrid Recommendation Based on Open-web Information , 2014, TREC.

[35]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[36]  Andrea Esuli,et al.  SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining , 2010, LREC.

[37]  ChengXiang Zhai,et al.  An exploration of axiomatic approaches to information retrieval , 2005, SIGIR '05.

[38]  Joydeep Ghosh,et al.  Review quality aware collaborative filtering , 2012, RecSys '12.

[39]  Qiang Wu,et al.  An exploration of ranking heuristics in mobile local search , 2012, SIGIR '12.

[40]  Mohamed F. Mokbel,et al.  Location-based and preference-aware recommendation using sparse geo-social networking data , 2012, SIGSPATIAL/GIS.

[41]  Daniel Marcu,et al.  Summarization beyond sentence extraction: A probabilistic approach to sentence compression , 2002, Artif. Intell..

[42]  Jaap Kamps,et al.  University of Amsterdam at the TREC 2013 Contextual Suggestion Track: Learning User Preferences from Wikitravel Categories , 2013, TREC.

[43]  Jimmy J. Lin,et al.  CWI and TU Delft Notebook TREC 2013: Contextual Suggestion, Federated Web Search, KBA, and Web Tracks , 2013, TREC.

[44]  Bo Pang,et al.  A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts , 2004, ACL.

[45]  M. Sanderson.  Book Reviews: Advances in Automatic Text Summarization , 2000, Computational Linguistics.

[46]  Hui Fang,et al.  An Opinion-aware Approach to Contextual Suggestion , 2013, TREC.

[47]  Jimmy J. Lin,et al.  CWI and TU Delft at TREC 2013: Contextual Suggestion, Federated Web Search, KBA, and Web Tracks , 2013 .

[48]  Hui Fang,et al.  An Exploraton of Ranking-Based Strategy for Contextual Suggestion , 2012, TREC.

[49]  Rodrygo L. T. Santos,et al.  The whens and hows of learning to rank for web search , 2012, Information Retrieval.