In this study, we propose a pipeline to analyse heterogeneity in selfdescriptions for the users of StockTwits, a microblogging platform about the stock market. By combining word and document embeddings with clustering methods, we aim to study what textual self-descriptions can reveal about users’ self-declared trading information. Preliminary results show that some patterns in texts reflect trading characteristics and encourage to explore the relation between textual and non textual self-description.
What does your self-description reveal about you? A pipeline to analyse StockTwits users.
Riccardo Ricciardi
2022-01-01
Abstract
In this study, we propose a pipeline to analyse heterogeneity in selfdescriptions for the users of StockTwits, a microblogging platform about the stock market. By combining word and document embeddings with clustering methods, we aim to study what textual self-descriptions can reveal about users’ self-declared trading information. Preliminary results show that some patterns in texts reflect trading characteristics and encourage to explore the relation between textual and non textual self-description.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
