Priberam

Opinion Mining in Newspapers and Blogs

Objectives

To build a system that extracts “opinions” from text in natural language. These can be opinions of politicians about controversial topics, opinions of bloggers about products, opinions expressed in Twitter, etc.

Description

Let’s consider the sentences “I just bought an iPhone. I love its camera and touch screen, even though it was expensive.” What is the opinion expressed in this piece of text? In this project, the goal is to extract opinions (i.e. find sentences like this among the huge amount of data on the Web), and obtain information such as the opinion holder, the aspect that is being opinionated about, and the opinion polarity (does it express a positive or negative sentiment?). In the example above, a positive opinion is expressed about the iPhone’s camera and screen, and a negative one about its price. In this project, your goal is to develop a computer program which does these tasks automatically.

Requisites

There are no mandatory requisites. Some programming experience (in languages like C/C++, Java, Python, Matlab, etc) is preferred.

Expected result

At the end of the project, the student should have created a system able to extract useful opinion information using sources such as blogs, forums, etc.

References

Opinion mining tutorial: http://www.cs.uic.edu/~liub/FBS/Sentiment-Analysis-tutorial-AAAI-2011.pdf A system that finds quotes in newspapers: http://voxx.sapo.pt/