Context-aware relevance feedback over SNS graph data

This study proposes a method for retrieving and ranking posts from social network services(SNSs) by specifying and providing feedback on the context of posts. Current search systems for SNS posts cannot handle user intent with regard to the context of posts to be retrieved, mainly owing to the incompleteness of SNS posts, i.e., they do not contain the users' contexts (e.g., situations or preferences) of users posting messages. Hence, we propose a search method that accepts two kinds of queries, namely, content queries and context queries, and that updates these queries based on the user feedback with special attention to the contexts of posts. Our search method considers the whole SNS dataset as a graph and the nodes surrounding each post as its context; to find relevant posts in terms of content and context, our method propagates user feedback via this graph. Our experimental results based on a Twitter test collection revealed that our proposed method showed improved retrieval performance as compared with conventional SNS retrieval and relevance feedback. In addition, we could detect the optimal parameters for feedback propagating.

[1]  Feng Liang,et al.  Exploiting real-time information retrieval in the microblogosphere , 2012, JCDL '12.

[2]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.

[3]  M. de Rijke,et al.  Incorporating Query Expansion and Quality Indicators in Searching Microblog Posts , 2011, ECIR.

[4]  Kazuhiro Seki,et al.  Improving pseudo-relevance feedback via tweet selection , 2013, CIKM.

[5]  Joemon M. Jose,et al.  Exploring term temporality for pseudo-relevance feedback , 2011, SIGIR.

[6]  Thomas Gottron,et al.  Searching microblogs: coping with sparsity and document quality , 2011, CIKM '11.

[7]  Sebastian Hellmann,et al.  Generating SPARQL queries using templates , 2013, Web Intell. Agent Syst..

[8]  Craig MacDonald,et al.  Identifying local events by using microblogs as social sensors , 2013, OAIR.

[9]  Yuefeng Li,et al.  Microblog Retrieval Using Topical Features and Query Expansion , 2011, TREC.

[10]  Katsumi Tanaka,et al.  Entity Identification on Microblogs by CRF Model with Adaptive Dependency , 2016 .

[11]  W. Bruce Croft,et al.  Temporal models for microblogs , 2012, CIKM.

[12]  Martine De Cock,et al.  Ranking Approaches for Microblog Search , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[13]  Miles Efron,et al.  Hashtag retrieval in a microblogging environment , 2010, SIGIR.

[14]  Eduard H. Hovy,et al.  Structured Event Retrieval over Microblog Archives , 2012, NAACL.

[15]  Joemon M. Jose,et al.  Temporal Pseudo-relevance Feedback in Microblog Retrieval , 2012, ECIR.

[16]  Harry Halpin,et al.  Relevance Feedback between Web Search and the Semantic Web , 2011, IJCAI.

[17]  Azadeh Shakery,et al.  Iterative Estimation of Document Relevance Score for Pseudo-Relevance Feedback , 2017, ECIR.

[18]  Katsumi Tanaka,et al.  Entity Identification on Microblogs by CRF Model with Adaptive Dependency , 2015, 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT).

[19]  Ting Wang,et al.  Improving Twitter Retrieval by Exploiting Structural Information , 2012, AAAI.

[20]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[21]  Mudhakar Srivatsa,et al.  Exploiting Relevance Feedback in Knowledge Graph Search , 2015, KDD.

[22]  Harry Shum,et al.  An Empirical Study on Learning to Rank of Tweets , 2010, COLING.

[23]  Vasudeva Varma,et al.  User context as a source of topic retrieval in Twitter , 2011 .

[24]  Thanh Tran,et al.  Heterogeneous web data search using relevance-based on the fly data integration , 2012, WWW.

[25]  Ben Carterette,et al.  Multiple testing in statistical analysis of systems-based information retrieval experiments , 2012, TOIS.

[26]  Heyan Huang,et al.  Query Expansion Based on a Feedback Concept Model for Microblog Retrieval , 2017, WWW.