Effectiveness of Six Text Classifiers for Predicting SET Stock Price Direction

Simple item page
dc.contributor.authorNetisopakul, Ponrudee
dc.contributor.authorSaewong, Woranun
dc.date.accessioned2026-08-06T10:27:30Z
dc.date.available2026-08-06T10:27:30Z
dc.date.issued2020-01-01
dc.description.abstractSix text classification methods were compared to find the best model for predicting Stock Exchange of Thailand stock prices. News headlines, on individual stocks, were classified as causing “change” and “no-change” based on a preset change threshold, 2.5%. The training dataset was collected by matching stock news in 2018 with stock names and filling in stock price changes. 258 news were associated with a “change” and 636 news with “no-change”. The Thai text news items were preprocessed and converted to TF-IDF vector representation. Six machine learning text classification methods are applied to create six text classifier models and create a confusion matrix, then compared with actual changes to obtain accuracy scores. We found that a deep learning classifier (with 85.6% accuracy) scored better than other classifiers for one day price movement to assist short-term investments.
dc.identifier.citationAdvances in Intelligent Systems and Computing, 1149 AISC, 104-118, 2020
dc.identifier.doi10.1007/978-3-030-44044-2_11
dc.identifier.issn21945357
dc.identifier.other2-s2.0-85083666528
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/10650
dc.sourceAdvances in Intelligent Systems and Computing
dc.subjectDecision tree
dc.subjectDeep learning
dc.subjectNaive Bayes
dc.subjectNeural network
dc.subjectRandom forest
dc.subjectStock news
dc.subjectStock trends
dc.subjectSVM
dc.subjectText classification
dc.titleEffectiveness of Six Text Classifiers for Predicting SET Stock Price Direction
dc.typeConference Paper

Files

Collections

Research