Association Analysis Between Public Sentiment and Grab Stock Performance Using SVM and Lambda Test

During a period of strong economic performance in Indonesia—marked by a 5.4% growth in the second quarter of 2022—concerns about a potential downturn in the fourth quarter began to surface, as indicated by increased stock market volatility, including fluctuations in Grab’s share prices. This study aims to classify public sentiment toward Grab based on comments from the social media platform Twitter, and to analyze its relationship with the direction of the company’s stock price movement. Sentiment classification was conducted using the Support Vector Machine (SVM) algorithm through a series of steps including data preprocessing, TF-IDF weighting, imbalance data handling, and model performance evaluation. The dataset was split into 70% training data and 30% testing data. The SVM model achieved an accuracy of 87%, with a precision of 90%, recall of 91%, and F1-score of 91%. Public sentiment for each period was then aggregated using the Net Sentiment Score (NSS), which was subsequently categorized into positive or negative sentiment. These sentiment categories were analyzed in relation to stock price movements using the Goodman-Kruskal Lambda test. The result of ????(stock∣sentiment)=0.053 indicates that knowing public sentiment reduces prediction error by only 5.3%, while ????(sentimen|saham)=0.000 shows no predictive value in the opposite direction. This study contributes a novel approach by integrating machine learning-based sentiment classification with a categorical association test, specifically applied to a regional technology company in Southeast Asia, which remains underexplored in existing literature.