skip to main content

Title: How does social media sentiment impact mass media sentiment? A study of news in the financial markets
Award ID(s):
2026583 1939088 1909803 1717473
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Journal of the Association for Information Science and Technology
Page Range / eLocation ID:
1183 to 1197
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. When COVID-19 first emerged in China, there was speculation that the outbreak would trigger public anger and weaken the Chinese regime. By analyzing millions of social media posts from Sina Weibo made between December 2019 and February 2020, we describe the contours of public, online discussions pertaining to COVID-19 in China. We find that discussions of COVID-19 became widespread on January 20, 2020, consisting primarily of personal reflections, opinions, updates, and appeals. We find that the largest bursts of discussion, which contain simultaneous spikes of criticism and support targeting the Chinese government, coincide with the January 23 lockdown of Wuhan and the February 7 death of Dr. Li Wenliang. Criticisms are directed at the government for perceived lack of action, incompetence, and wrongdoing—in particular, censoring information relevant to public welfare. Support is directed at the government for aggressive action and positive outcomes. As the crisis unfolds, the same events are interpreted differently by different people, with those who criticize focusing on the government’s shortcomings and those who praise focusing on the government’s actions. 
    more » « less
  2. null (Ed.)
    Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner. It has in general two sub-tasks: (i) extracting aspects from each review, and (ii) classifying aspect-based reviews by sentiment polarity. In this pa-per, we propose a weakly-supervised approach for aspect-based sentiment analysis, which uses only a few keywords describing each aspect/sentiment without using any labeled examples. Existing methods are either designed only for one of the sub-tasks, neglecting the benefit of coupling both, or are based on topic models that may contain overlapping concepts. We propose to first learn sentiment, aspectjoint topic embeddings in the word embedding space by imposing regularizations to encourage topic distinctiveness, and then use neural models to generalize the word-level discriminative information by pre-training the classifiers with embedding-based predictions and self-training them on unlabeled data. Our comprehensive performance analysis shows that our method generates quality joint topics and outperforms the baselines significantly (7.4%and 5.1% F1-score gain on average for aspect and sentiment classification respectively) on benchmark datasets. 
    more » « less
  3. null (Ed.)
  4. Research has shown that accounting for moral sentiment in natural language can yield insight into a variety of on- and off-line phenomena such as message diffusion, protest dynamics, and social distancing. However, measuring moral sentiment in natural language is challenging, and the difficulty of this task is exacerbated by the limited availability of annotated data. To address this issue, we introduce the Moral Foundations Twitter Corpus, a collection of 35,108 tweets that have been curated from seven distinct domains of discourse and hand annotated by at least three trained annotators for 10 categories of moral sentiment. To facilitate investigations of annotator response dynamics, we also provide psychological and demographic metadata for each annotator. Finally, we report moral sentiment classification baselines for this corpus using a range of popular methodologies. 
    more » « less