{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emtagger-a-word-embedding-based-novel-method","title":"EmTaggeR: A Word Embedding Based Novel Method for Hashtag Recommendation on Twitter","arxiv_id":"1712.01562","date":"2017-12-05","proceeding":null,"authors":["Kuntal Dey","Ritvik Shrivastava","Saroj Kaushik","L. Venkata Subramaniam"],"abstract":"The hashtag recommendation problem addresses recommending (suggesting) one or\nmore hashtags to explicitly tag a post made on a given social network platform,\nbased upon the content and context of the post. In this work, we propose a\nnovel methodology for hashtag recommendation for microblog posts, specifically\nTwitter. The methodology, EmTaggeR, is built upon a training-testing framework\nthat builds on the top of the concept of word embedding. The training phase\ncomprises of learning word vectors associated with each hashtag, and deriving a\nword embedding for each hashtag. We provide two training procedures, one in\nwhich each hashtag is trained with a separate word embedding model applicable\nin the context of that hashtag, and another in which each hashtag obtains its\nembedding from a global context. The testing phase constitutes computing the\naverage word embedding of the test post, and finding the similarity of this\nembedding with the known embeddings of the hashtags. The tweets that contain\nthe most-similar hashtag are extracted, and all the hashtags that appear in\nthese tweets are ranked in terms of embedding similarity scores. The top-K\nhashtags that appear in this ranked list, are recommended for the given test\npost. Our system produces F1 score of 50.83%, improving over the LDA baseline\nby around 6.53 times, outperforming the best-performing system known in the\nliterature that provides a lift of 6.42 times. EmTaggeR is a fast, scalable and\nlightweight system, which makes it practical to deploy in real-life\napplications.","url_abs":"http://arxiv.org/abs/1712.01562v1","url_pdf":"http://arxiv.org/pdf/1712.01562v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emtagger-a-word-embedding-based-novel-method","repo_url":"https://github.com/0xyd/sec2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"tag","task_name":"TAG"}],"methods":[{"method_slug":"lda","method_name":"LDA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}