Recommendation algorithms automatically suggest news articles based on past behavioral logs. There has been reported cases of mental health problems caused by continuous consumption of negative articles, besides recommendation algorithms has a problem of over-recommendation which may induce continuous consumption of negative articles. Although research on the relationship between negative news article consumption and mental health has been conducted via small-scale user interviews, large-scale behavioral research on user engagement with recommended news articles has not been carried out. Therefore, we comprehensively investigated how the emotional polarity of articles affects each indicator of user attention by assigning emotional labels to news articles using crowdsourcing and analyzing about 1 million user behavior logs that viewed these articles. To the best of our knowledge, this is one of the first publicly available studies to analyze the impact of negative articles on users' news consumption behavior on an online news platform. The findings indicated that negative articles, irrespective of their category, were more likely to be clicked on, were read for longer durations, and had lower bounce rates. Furthermore, users showed greater interest in negative news related to entertainment and sports. These findings can be used as a first step for news platforms to build safer recommendation algorithms that consider the psychological impact on users.

We present a new morphological analy-sis model that considers semantic plausi-bility of word sequences by using a re-current neural network language model (RNNLM). In unsegmented languages, since language models are learned from automatically segmented texts and in-evitably contain errors, it is not apparent that conventional language models con-tribute to morphological analysis. To solve this problem, we do not use language mod-els based on raw word sequences but use a semantically generalized language model, RNNLM, in morphological analysis. In our experiments on two Japanese corpora, our proposed model significantly outper-formed baseline models. This result indi-cates the effectiveness of RNNLM in mor-phological analysis. 1