TY - JOUR

T1 - PyFin-sentiment

T2 - Towards a machine-learning-based model for deriving sentiment from financial tweets

AU - Wilksch, Moritz

AU - Abramova, Olga

N1 - Publisher Copyright: © 2023 The Author(s)

PY - 2023/4/1

Y1 - 2023/4/1

N2 - Responding to the poor performance of generic automated sentiment analysis solutions on domain-specific texts, we collect a dataset of 10,000 tweets discussing the topics of finance and investing. We manually assign each tweet its market sentiment, i.e., the investor's anticipation of a stock's future return. Using this data, we show that all existing sentiment models trained on adjacent domains struggle with accurate market sentiment analysis due to the task's specialized vocabulary. Consequently, we design, train, and deploy our own sentiment model. It outperforms all previous models (VADER, NTUSD-Fin, FinBERT, TwitterRoBERTa) when evaluated on Twitter posts. On posts from a different platform, our model performs on par with BERT-based large language models. We achieve this result at a fraction of the training and inference costs due to the model's simple design. We publish the artifact as a python library to facilitate its use by future researchers and practitioners.

AB - Responding to the poor performance of generic automated sentiment analysis solutions on domain-specific texts, we collect a dataset of 10,000 tweets discussing the topics of finance and investing. We manually assign each tweet its market sentiment, i.e., the investor's anticipation of a stock's future return. Using this data, we show that all existing sentiment models trained on adjacent domains struggle with accurate market sentiment analysis due to the task's specialized vocabulary. Consequently, we design, train, and deploy our own sentiment model. It outperforms all previous models (VADER, NTUSD-Fin, FinBERT, TwitterRoBERTa) when evaluated on Twitter posts. On posts from a different platform, our model performs on par with BERT-based large language models. We achieve this result at a fraction of the training and inference costs due to the model's simple design. We publish the artifact as a python library to facilitate its use by future researchers and practitioners.

KW - Deep learning

KW - Financial market sentiment

KW - Machine learning

KW - Opinion mining

KW - Sentiment analysis

KW - Business informatics

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=85150288650&partnerID=8YFLogxK

U2 - 10.1016/j.jjimei.2023.100171

DO - 10.1016/j.jjimei.2023.100171

M3 - Journal articles

AN - SCOPUS:85150288650

VL - 3

JO - International Journal of Information Management Data Insights

JF - International Journal of Information Management Data Insights

SN - 2667-0968

IS - 1

M1 - 100171

ER -