Find right countenance for your input—Improving automatic emoticon recommendation system with distributed representations

作者：

Highlights：

• Adapted pre-trained model (i.e. BERT, ELMo, and Word2vec) learned from Japanese data to our emoticon recommendation system.

• Empirically compared our proposed systems with baseline methods that learned surface patterns of texts and emoticons.

• Compared pre-trained models learned from different text domains to observe the difference in recommendation results.

摘要

•Adapted pre-trained model (i.e. BERT, ELMo, and Word2vec) learned from Japanese data to our emoticon recommendation system.•Empirically compared our proposed systems with baseline methods that learned surface patterns of texts and emoticons.•Compared pre-trained models learned from different text domains to observe the difference in recommendation results.

论文关键词：Emoticons,Affective computing,Recommendation systems,Distributed representations

论文评审过程：Received 28 May 2020, Revised 25 September 2020, Accepted 14 October 2020, Available online 5 November 2020, Version of Record 5 November 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2020.102414