Text Mining of Stocktwits Data for Predicting Stock Prices

TL;DR

This paper introduces FinALBERT, a specialized financial text classification model trained on Stocktwits data to improve stock price prediction by understanding market sentiment.

Contribution

The paper presents FinALBERT, a novel ALBERT-based model fine-tuned on labeled Stocktwits data for financial sentiment analysis and stock movement prediction.

Findings

FinALBERT outperforms traditional models in sentiment classification.

Labeling techniques effectively capture stock price change signals.

Model demonstrates adaptability across different architectures.

Abstract

Stock price prediction can be made more efficient by considering the price fluctuations and understanding the sentiments of people. A limited number of models understand financial jargon or have labelled datasets concerning stock price change. To overcome this challenge, we introduced FinALBERT, an ALBERT based model trained to handle financial domain text classification tasks by labelling Stocktwits text data based on stock price change. We collected Stocktwits data for over ten years for 25 different companies, including the major five FAANG (Facebook, Amazon, Apple, Netflix, Google). These datasets were labelled with three labelling techniques based on stock price changes. Our proposed model FinALBERT is fine-tuned with these labels to achieve optimal results. We experimented with the labelled dataset by training it on traditional machine learning, BERT, and FinBERT models, which helped us understand how these labels behaved with different model architectures. Our labelling method competitive advantage is that it can help analyse the historical data effectively, and the mathematical function can be easily customised to predict stock movement.