#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7811–7820 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 7811 #HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention Yuji Zhang1 Yubo Zhang1 Chunpu Xu1 Jing Li1∗Ziyan Jiang2† Baolin Peng3 1Department of Computing, The Hong Kong Polytechnic University, HKSAR, China 2Amazon Alexa AI, Seattle, WA 3Microsoft Research, Redmond, WA 1{yu-ji.zhang, yubo.zhang, chun-pu.xu}@connect.polyu.hk 1jing-amelia.li@polyu.edu.hk 2ziyjiang@amazon.com 3bapeng@microsoft.com Abstract Millions of hashtags are created on social me- dia every day to cross-refer messages concern- ing similar topics. To help people find the top- ics they want to discuss, this paper character- izes a user’s hashtagging preferences via pre- dicting how likely they will post with a hash- tag. It is hypothesized that one’s interests in a hashtag are related to what they said before (user history) and the existing posts present the hashtag (hashtag contexts). These factors are married in the deep semantic space built with a pre-trained BERT and a neural topic model via joint training. In this way, user interests learned from the past can be customized to match future hashtags, which is beyond the capability of existing methods assuming un- changed hashtag semantics. Furthermore, we propose a novel personalized topic attention to capture salient contents to personalize hashtag contexts. Experiments on a large-scale Twitter dataset show that our model significantly out- performs the state-of-the-art recommendation approach without exploiting latent topics.1 1 Introduction Virtual communications are playing an increasingly crucial role in our daily activities. In this profound revolution in interpersonal communications, social media has become the key channel to connect an individual with human society. People are now turning to the online world to exchange viewpoints, voice opinions, and engage in topics they are in- terested in. Nonetheless, the deluge of the online contents streaming through social media every day has presented the concrete challenges for users to catch what they essentially need. ∗Jing Li is the corresponding author. † This work was mainly conducted before Ziyan Jiang joined Amazon. 1Our dataset and code are publicly avail- able in https://github.com/polyusmart/ Personalized-Hashtag-Preferences Sample tweets in H’s hashtag contexts. Love thriller and mystery? Check out: URL She is writing the end for a long time. 85-5 star review! Why not visit for Sunday share? Sample tweets in U’s user history. Darpocalypse is now available as an ebook! Read book 2 in the epic living dead series. Zombie Thriller Apocalypse Reader: Zeke is a skilled lover, so easy to fall for. But he has a dark & twisted nature. Figure 1: The hashtag context snippet of #book (H) is shown on the top and the target user U’s hashtag- ging history snippet on the bottom. U later tweeted and tagged H. The topic words indicating U’s hashtagging preferences are in italic and blue, so is the tweet in H’s context implying its potential to be engaged with U. To deal with this issue, many platforms encour- age users to tag their messages with hashtags (e.g., “#COVID19” and “#NLPeople”) — topic …

Content truncated to 500 words