Research

Your Network Is Your Tweet Worth

Abstract: This paper investigates how social media affects financial markets by seeking out the grounds of financial social media prediction power. The first goal of this study is to understand the impact of the position in the social network in gathering superior information about future stock returns. In other words, I focus on the relationship between investors' network centrality and investors' ability to predict future stock returns.

Keywords: Sentiment Analysis, NLP, Machine Learning, Text Analysis, Microblogs, Text Classification, Skills, Mixture Distributions, Networks

Conferences: -

Number of Pages: 59Date Written: 18 Oct 2022Last Revised: 1 Mar 2023

When the `Dumb’ Crowd Beats the `Smart’ Crowd

Abstract: This paper focuses on the skills of social media users in issuing investment recommendations. On average, the recommendations of users translate into positive abnormal returns. The cross-section of skills across stocks outperforms, on average, the cross-section of skills across users. Modeling users’ performance with Gaussian mixture distributions for several skill groups shows that the large majority of users exhibit positive skills, outperforming the skills of qualified financial website authors. Social media user communities demonstrate heterogeneous skills due to several determinants, including analyzing news events, experience, the number of recommendations issued, and the number of users’ followers.

Keywords: Sentiment analysis, NLP, Machine Learning, Text Analysis, Microblogs, Text Classification, Skills, Mixture Distributions

Conferences: World Finance Conference 2022, Young Swiss Economist Meeting 2022, SSES Annual Congress 2022

Number of Pages: 52Date Written: 10 Sep 2021Last Revised: 1 Mar 2023

Do Actions Speak Louder than Words? Evidence from Microblogs

Abstract: This research identifies the determinants of investors' future beliefs by analyzing more than 50 million tweets on thousands of stocks from the microblogging platform StockTwits. To distinguish between the different sources of changes in beliefs, I divide tweets into two categories: beliefs, representing the average sentiment of all investors regarding a particular stock, and actions, representing the actual transactions disclosed by StockTwits' users in their tweets. The results show that investors’ average next-period beliefs are positively impacted by the average sentiment (beliefs and actions) of the previous day. The effect is stronger once the quality of the investment advice is taken into account. Finally, more communication between investors is associated with greater diversity in beliefs as well as higher uncertainty.

Keywords: Sentiment Analysis, NLP, Text Analysis, Microblogs, Text Classification, Herding, Word-of-Mouth

Conferences: EFA Poster Session: 47th Annual Meeting of the European Finance Association

Number of Pages: 38Date Written: 1 Mar 2019Last Revised: 31 Dec 2021