Social Text-Driven Stock Prediction in Indonesian

It is an Indonesian dataset for predicting stock trends by crawling stock prices from Yahoo Finance and social texts from Twitter using Tweepy. It is manually reviewed from the CIKM18 ChatGPT-translated dataset, predicting stocks based on Twitter news, labeled “naik (rise)” or “turun (fall)”.

该数据集为面向股票趋势预测的印尼语数据集，通过Tweepy从Twitter抓取社交文本，并从雅虎财经（Yahoo Finance）爬取股票价格以获取数据。该数据集源自CIKM18的ChatGPT翻译数据集并经过人工审核，依托Twitter相关新闻开展股票预测任务，标注标签为“naik（上涨，rise）”或“turun（下跌，fall）”。