Twitter Sentiment on Mispricing in Indonesia Stock Market

Long / Short Strategies Following Sentiment

DOI

10.2991/aebmr.k.201126.056How to use a DOI?

Keywords

twitter sentiment, anomaly, long-short strategies, mispricing, machine learning

Abstract

This paper examines the relationship between twitter sentiment on mispricing in Indonesia listed firms over period 2013 – 2017. This study uses machine learning method to classify sentiments based on Naïve Bayes, Support Vector Machine and Decision Tree algorithm. The results show that Decision Tree is the best method to classify sentiment in Indonesian. To measure mispricing, we use mispricing score method from Stambaugh Yu and Yuan 2012 associated with 9 long/short anomalies. The results of this experimental studies show that sentiment exhibits significant relation to stock returns on the long/short strategies. The short-leg strategy is more profitable following low or positive sentiment.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lusiana Indra
AU  - Zaafri Ananto Husodo
PY  - 2020
DA  - 2020/11/27
TI  - Twitter Sentiment on Mispricing in Indonesia Stock Market
BT  - Proceedings of the 5th Padang International Conference On Economics Education, Economics, Business and Management, Accounting and Entrepreneurship (PICEEBA-5 2020)
PB  - Atlantis Press
SP  - 501
EP  - 509
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.201126.056
DO  - 10.2991/aebmr.k.201126.056
ID  - Indra2020
ER  -