A Two-Dimensional Sentiment Analysis of Online Public Opinion and Future Financial Performance of Publicly Listed Companies

Meng‐Feng ‐F Yen, Yu‐Pei ‐P Huang, Liang‐Chih ‐C Yu, Yueh‐Ling ‐L Chen

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Based on a two-dimensional valence-arousal sentiment evaluation method, we used the sentiment extracted from the text of online news media and stock forums to predict future financial performance of publicly listed companies. A Chinese lexicon called the Chinese Valence-Arousal Words, provided by Yu et al. (2016), was used to obtain the valence and arousal scores of all Web text for each of the 183 large listed companies for each fiscal quarter over the Q1 2013 through Q3 2017 period. Our empirical results tended to support our two hypotheses that there is a positive association between the valence (under Hypothesis 1) or arousal-augmented valence (under Hypothesis 2) of online public opinion about the listed companies and their future financial performance. In particular, when the sentiment was positive (negative) in the current fiscal quarter, whether measured by the valence alone or by the arousal-augmented valence, the financial performance (measured by ROA, ROE, and Tobin’s Q) observed in the next quarter would tend to be better (worse).

Original languageEnglish
JournalComputational Economics
DOIs
Publication statusAccepted/In press - 2021

All Science Journal Classification (ASJC) codes

  • Economics, Econometrics and Finance (miscellaneous)
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A Two-Dimensional Sentiment Analysis of Online Public Opinion and Future Financial Performance of Publicly Listed Companies'. Together they form a unique fingerprint.

Cite this