This courselet will cover how to assess and capture sentiment with regards to news article publications via supervised machine learning methods and dictionary based methods
Sentiment analysis, which can also be referred to as opinion mining, is a field in Natural Language Processing that identifies the sentiment of a text document. Sentiment analysis is a popular field for companies to determine and categorize opinions about a product or a service.
In this courselet, we will cover 5 different sentiment analysis methods. In particular, we will compare supervised machine learning methods to dictionary-based methods. This courselet also compares non-contextual text representations to contextual text representations as inputs for the supervised machine learning methods, to examine, whether context can improve the assessment of sentiment with regards to news article publications.
As a result, the participants will get a first insight into sentiment analysis methods. In addition, our courselet participants will learn about different ways on how to assess sentiment in text documents. All codes are available on quantlet.com.
Graduate Student of Economics and Management Science at Humboldt University of Berlin
Research Interests:
Sentiment Analysis
NLP
Quantitative Finance