Short text processing workbench

Short text processing workbench

 

The wide use of social media has rendered the processing of short texts significant in tasks like opinion, sentiment, and topic detection.

In this project, you will work on a framework for processing collections of short texts where you will use NLP and Graph techniques to reveal information. The framework will be built using Python which provides rich libraries for these purposes. You will work on various collections of short texts to extract information about the relevant persons and issues. You will use Wikidata to support semantic processing.

There are numerous visualizations that are of interest, such as the following heatmap that shows the issues extracted from tweets collected during the same period for consecutive days. Such visualizations facilitate the comprehension of issues that emerge from large collections of tweets, which is very difficult to understand manually.

 

Heatmap of COVID related issues in Tweets

Project Advisor: 

Suzan Üsküdarlı

Project Status: 

Project Year: 

2020
  • Fall

Contact us

Department of Computer Engineering, Boğaziçi University,
34342 Bebek, Istanbul, Turkey

  • Phone: +90 212 359 45 23/24
  • Fax: +90 212 2872461
 

Connect with us

We're on Social Networks. Follow us & get in touch.