Abstract
Social media services make it possible for an increasing number of people to express their opinion publicly. In this context, large amounts of hateful comments are published daily. The PHARM project aims at monitoring and modeling hate speech against refugees and migrants in Greece, Italy, and Spain. In this direction, a web interface for the creation and the query of a multi-source database containing hate speech-related content is implemented and evaluated. The selected sources include Twitter, YouTube, and Facebook comments and posts, as well as comments and articles from a selected list of websites. The interface allows users to search in the existing database, scrape social media using keywords, annotate records through a dedicated platform and contribute new content to the database. Furthermore, the functionality for hate speech detection and sentiment analysis of texts is provided, making use of novel methods and machine learning models. The interface can be accessed online with a graphical user interface compatible with modern internet browsers. For the evaluation of the interface, a multifactor questionnaire was formulated, targeting to record the users’ opinions about the web interface and the corresponding functionality.
Highlights
In today’s ubiquitous society, we experience a situation where digital informing and mediated communication are dominant
As a core objective of the Preventing Hate against Refugees and Migrants (PHARM) project is to build a software environment for querying, analyzing, and storing multi-source news and social media content focusing on hate speech against migrants and refugees, a set of scripts for Natural Language Processing (NLP) has been developed, along with a web service that enables friendly user interaction
It is the graphical interface for exposing data and functionality to the users and relies on the back-end, which consists of the PHARM scripts
Summary
In today’s ubiquitous society, we experience a situation where digital informing and mediated communication are dominant. Regarding social media, which since their emergence have experienced a vast expansion and are registered as an everyday common practice for thousands of people, the ease of use along with the immediacy they present made them extremely popular. In any of their modes, such as microblogging (like Twitter), photos oriented (like Instagram), etc., they are largely accepted as fast forms of communication and news dissemination through a variety of devices. In an area that is so wide and accessible to large audiences many improper intentions with damaging effects might be met as well, one of which is hate speech
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
