像很多互联网时代的产物一样，Emoji 从开始被大众使用到现在铺天盖地只用了不到十年的时间。在这段时间里，Emoji 改变了我们交流的方式，重新定义了网络书写语言的规则。表情符号并不简简单单的表示感情，而是微妙的影响着语义和交互的体验。只有当我们真正理解了 Emoji 和语言的交互，才能打造能够自然使用 Emoji 的聊天机器人，atv，才能让真正让人工智能理解数字时代的我们。

　　参考文献

Davidov, D., Tsur,O., & Rappoport, A. (2010, August). Enhanced sentiment learning usingtwitter hashtags and smileys. In Proceedingsof the 23rd international conference on computational linguistics: posters (pp. 241-249). Association forComputational Linguistics.

Ganster, T., Eimler,S. C., & Krämer, N. C. (2012). Same same but different!? The differentialinfluence of smilies and emoticons on person perception. Cyberpsychology, Behavior, andSocial Networking, 15(4),226-230.

Kralj Novak, P.,Smailovi?, J., Sluban, B., Mozeti?, I., Liu, B., Liu, B., … Good, I. (2015).Sentiment of Emojis. PLOS ONE, 10(12), e0144296. https://doi.org/10.1371/journal.pone.0144296

Tian, Y., Galery,T., Dulcinati, G., Molimpakis, E., & Sun, C. (2017). Facebook emotions:Reactions and Emojis. In Proceedings of the EACL 2017 Workshop on NaturalLanguage Processing for Social Media (SocialNLP).

Zhao, J., Dong, L., Wu, J., & Xu, K.(2012). MoodLens: An Emoticon-Based Sentiment Analysis System for ChineseTweets. Proceedings of the 18th ACM SIGKDD International Conference onKnowledge Discovery and Data Mining - KDD ’12, 1528–1531. https://doi.org/10.1145/2339530.2339772

关于PaperWeekly

PaperWeekly 是一个分享知识和交流学问的学术组织，关注的领域是 NLP 的各个方向。如果你也经常读 paper，喜欢分享知识，喜欢和大家一起讨论和学习的话，请速速来加入我们吧。