Implicit Linking of Food Entities in Social Media

Dining is an important part in people’s lives and this explains why food-related microblogs and reviews are popular in social media. Identifying food entities in food-related posts is important to food lover profiling and food (or restaurant) recommendations. In this work, we conduct Implicit Entity Linking (IEL) to link food-related posts to food entities in a knowledge base. In IEL, we link posts even if they do not contain explicit entity mentions. We first show empirically that food venues are entity-focused and associated with a limited number of food entities each. Hence same-venue posts are likely to share common food entities. Drawing from these findings, we propose an IEL model which incorporates venue-based query expansion of test posts and venue-based prior distributions over entities. In addition, our model assigns larger weights to words that are more indicative of entities. Our experiments on Instagram captions and food reviews shows our proposed model to outperform competitive baselines.

[1]  Paolo Ferragina,et al.  TAGME: on-the-fly annotation of short text fragments (by wikipedia entities) , 2010, CIKM.

[2]  Arkaitz Zubiaga,et al.  Exploiting Geolocation, User and Temporal Information for Natural Hazards Monitoring in Twitter , 2015, Proces. del Leng. Natural.

[3]  D G T Denison,et al.  Weighted naive Bayes modelling for data miningJ , 2001 .

[4]  W. Bruce Croft,et al.  Query expansion using local and global document analysis , 1996, SIGIR '96.

[5]  Wei Shen,et al.  LIEGE:: link entities in web lists with knowledge base , 2012, KDD.

[6]  Qiaozhu Mei,et al.  PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks , 2015, KDD.

[7]  Wei Shen,et al.  LINDEN: linking named entities with knowledge base via semantic knowledge , 2012, WWW.

[8]  Heng Ji,et al.  Collective Tweet Wikification based on Semi-supervised Graph Regularization , 2014, ACL.

[9]  Tat-Seng Chua,et al.  Resolving local cuisines for tourists with multi-source social media contents , 2014, Multimedia Systems.

[10]  Hans-Peter Frei,et al.  Concept based query expansion , 1993, SIGIR.

[11]  Wei Shen,et al.  Linking named entities in Tweets with knowledge base via user interest modeling , 2013, KDD.

[12]  Ee-Peng Lim,et al.  Tweet Geolocation: Leveraging Location, User and Peer Signals , 2017, CIKM.

[13]  Ee-Peng Lim,et al.  Collective Entity Linking in Tweets Over Space and Time , 2017, ECIR.

[14]  M. de Rijke,et al.  Adding semantics to microblog posts , 2012, WSDM '12.

[15]  Geoffrey I. Webb,et al.  Alleviating naive Bayes attribute independence assumption by attribute weighting , 2013, J. Mach. Learn. Res..

[16]  Paolo Ferragina,et al.  From TagME to WAT: a new entity annotator , 2014, ERD '14.

[17]  Amit P. Sheth,et al.  Implicit Entity Linking in Tweets , 2016, ESWC.

[18]  Prasenjit Majumder,et al.  Query Expansion for Microblog Retrieval , 2011, TREC.

[19]  Ian H. Witten,et al.  An effective, low-cost measure of semantic relatedness obtained from Wikipedia links , 2008 .

[20]  Ming-Wei Chang,et al.  Entity Linking on Microblogs with Spatial and Temporal Signals , 2014, TACL.

[21]  Yitong Li,et al.  Entity Linking for Tweets , 2013, ACL.