Project: Discovering lever on safty in Netherlands based on social media data

The Information Systems group is often contacted by industrial organizations with assignments that could lead to student projects at various levels (master thesis project, bachelor completion project, etc.) Through this website we make these topics available to our students. In this post, we announce one such project, involving companies NIPPUR and AD.

Every year Algemeen Dagblad (AD) and its subsidiaries report in the newspaper and online on crime and perception of security of Dutch residents. This report is called ‘Crimewatch’ or ‘AD Misdaadmeter’. The articles are due somewhere February/March of each year.
The content is prepared by research journalists. They focus primarily on quantitative data. Data is received from the National Police.
AD would like to extend these reports by involving new sources to enhance to quality of the reports and by introducing new methods and techniques that allow to add new angles in reporting.

AD would like to extend the reports by datamining relevant text oriented data that can be found on the internet. To add the ‘sentiment’ of the people of the Netherlands about the topics mentioned.
Nowadays it is possible to collect social media data (as available on 100s of thousands websites e.g. Twitter, Facebook, Linkedin, blog posts etc etc). Next techniques exist to analyse these texts and determine positive or negative sentiment and corresponding confidence of prediction. In many messages additional information can be found to further analyse this data and determine certain topics of interest and geographical locations.
For AD it could be very interesting to determine what people are talking about when crime is concerned and how they feel about it. To investigate the relationship between actual crime and the perception of the people. If possible zooming in on specific topics and regions.

Student requirements:

  • dutch knowledge

Contact for more information: Anna Wilbik