Chatbots for Sentiment Analytics

This chapter starts with outlining the importance of unstructured data in finance and FinTech. Then, linking the text data format to be one of the components of such unstructured dataframes. Next section introduces the reader to base techniques handling words and sentences utilizing tokenization approach. This exposition is supported by Python code snippets and graphical result representation. Then, we move toward language model implementation, VADER . We do not step into the mathematical definitions at this stage, however, we focus our attention on model usage and result interpretation. Lastly, we expose the reader to a rather more sophisticated model, FinBERT .