Conference Proceeding Article
Microblogging services allow users to create hashtags to categorize their posts. In recent years,the task of recommending hashtags for microblogs has been given increasing attention. However,most of existing methods depend on hand-crafted features. Motivated by the successful use oflong short-term memory (LSTM) for many natural language processing tasks, in this paper, weadopt LSTM to learn the representation of a microblog post. Observing that hashtags indicatethe primary topics of microblog posts, we propose a novel attention-based LSTM model whichincorporates topic modeling into the LSTM architecture through an attention mechanism. Weevaluate our model using a large real-world dataset. Experimental results show that our modelsignificantly outperforms various competitive baseline methods. Furthermore, the incorporationof topical attention mechanism gives more than 7.4% improvement in F1 score compared withstandard LSTM method.
Digital Communications and Networking | Graphics and Human Computer Interfaces | Social Media
Proceedings of the 26th International Conference on Computational Linguistics: Osaka, Japan, 2016 December 11-16
City or Country
LI, Yang; LIU, Ting; Jing JIANG; and ZHANG, Liang.
Hashtag recommendation with topical attention-based LSTM. (2016). Proceedings of the 26th International Conference on Computational Linguistics: Osaka, Japan, 2016 December 11-16. 943-952. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3436
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.