Social Network Financial Behavior Prediction
Project Overview
With the rapid growth of the Internet, the amount of text data has also grown exponentially. This data can be used to obtain information for decision-making. Text analysis can effectively obtain potential information, which may include public opinion, product usage opinions, or market trend information. How to extract important features from text is a major challenge.
This project will apply neural methods to the text feature extraction model: Neural Network Language Model, to obtain features based on the n-gram model concept. Eventually, it will combine the Time Series perspective to analyze the public emotion and reactions of Taiwanese people to specific financial issues in real time, and explore whether the public emotion in virtual communities has a time series lag effect on specific events.
