Temporal enhanced sentence‐level attention model for hashtag recommendation. Issue 2 (1st June 2018)

• Record Type: Journal Article
• Authors: Ma, Jun; Feng, Chong; Shi, Ge; Shi, Xuewen; Huang, Heyang
• Is Part Of: CAAI transactions on intelligence technology. Volume 3:Issue 2(2018)
• Page Start: 95
• Page End: 100
• Publication Date: 2018-06-01
• Subjects: information retrieval -- social networking (online) -- recommender systems -- natural language processing -- pattern classification -- text analysis; temporal enhanced sentence‐level attention model -- natural language processing tasks -- training corpus -- social networks -- sample statistics -- social media -- wrong labels -- classifier -- microblog hashtag -- temporal hashtags -- temporal enhanced selective sentence‐level attention -- wrong labelled microblogs -- SINA Weibo microblogs -- hashtag recommendation; C6130D Document processing techniques -- C6180N Natural language processing -- C7210N Information networks -- C7250R Information retrieval techniques; Artificial intelligence -- Periodicals; Computer science -- Periodicals; Artificial intelligence; Computer science; Electronic journals; Periodicals; 006.305
• DOI: 10.1049/trit.2018.0012
• Languages: English
• ISSNs: 2468-6557

Abstract

Abstract : Hashtags of microblogs can provide valuable information for many natural language processing tasks. How to recommend reliable hashtags automatically has attracted considerable attention. However, existing studies assumed that all the training corpus crawled from social networks are labelled correctly, while large sample statistics on real social media shows that there are 8.9% of microblogs with hashtags having wrong labels. The notable influence of noisy data to the classifier is ignored before. Meanwhile, recency also plays an important role in microblog hashtag, but the information is not used in the existing studies. Some temporal hashtags such as World Cup will ignite at a particular time, but at other times, the number of people talking about it will sharply decrease. To address the twofold shortcomings above, the authors propose an long short‐term memory‐based model, which uses temporal enhanced selective sentence‐level attention to reduce the influence of wrong labelled microblogs to the classifier. Experimental results using a dataset of 1.7 million microblogs collected from SINA Weibo microblogs demonstrated that the proposed method could achieve significantly better performance than the state‐of‐the‐art methods.