Chen, C.-C.C.-C.ChenHuang, H.-H.H.-H.HuangHSIN-HSI CHEN2021-05-052021-05-052019https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076998642&doi=10.1145%2f3341161.3342945&partnerID=40&md5=28b4399a64ca99174cd8aa60782b6923https://scholars.lib.ntu.edu.tw/handle/123456789/558906Social trading platforms provide a forum for investors to share their analysis and opinions. Posts on these platforms are characterized by narrative styles which are much different from posts on general social platforms, for instance tweets. As a result, recommendation systems for social trading platforms should leverage tailor-made latent features. This paper presents a representation for these latent features in both textual data and market information. A real-world dataset is adopted to conduct experiments involving a novel task called next cashtag prediction. We propose a joint learning model with an attentive capsule network. Experimental results show positive results with the proposed methods and the corresponding auxiliary tasks. © 2019 Association for Computing Machinery.Interest prediction; Joint learning; Social tradingForecasting; Interest predictions; Joint learning; Market information; Novel task; Real-world; Social trading; Textual data; Trading platform; Commerceconference paper10.1145/3341161.33429452-s2.0-85076998642