Automated investor sentiment classification using financial social media

Aitong Zhong, Qiwei Han

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

As Fintech continuously disrupt the finance industry, big data from non-traditional sources have been increasingly used to extract investment signals with automated solutions. We leverage a large-scale user post dataset from a financial social media platform and to predict investor sentiment using the natural language processing techniques and machine learning models. The BERT model built and fine-tuned on texts from finance domain outperforms existing baseline models and provides 86% of accuracy to correctly predict investor sentiment. Our results show that automated investor sentiment classification needs to built with both complex machine learning models and with good quality fiancnial data.

Original languageEnglish
Title of host publicationProceedings - 2021 2nd International Conference on Computing and Data Science, CDS 2021
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages356-361
Number of pages6
ISBN (Electronic)9781665404280
DOIs
Publication statusPublished - Jan 2021
Event2nd International Conference on Computing and Data Science, CDS 2021 - Stanford, United States
Duration: 28 Jan 202129 Jan 2021

Publication series

NameProceedings - 2021 2nd International Conference on Computing and Data Science, CDS 2021

Conference

Conference2nd International Conference on Computing and Data Science, CDS 2021
Country/TerritoryUnited States
CityStanford
Period28/01/2129/01/21

Keywords

  • Deep natural language processing
  • Financial social media
  • Investor sentiment

Fingerprint

Dive into the research topics of 'Automated investor sentiment classification using financial social media'. Together they form a unique fingerprint.

Cite this