Reducing the moderation effort of user comments with the help of automation using text analytical methods (MODERAT!) (MODERAT!)

Basic data for this project

Description

In recent years, a rapid increase in racist, political and religiously motivated hate commentaries has led many newspaper editors to deactivate their online comment function on their websites. While this is understandable from an economic point of view for the individual publishers, in view of the restriction rates of up to 50% there are serious problems for the public discourse. The MODERAT! project uses an interactive and interdisciplinary approach to develop software tools and a practice-oriented web platform that enable platform operators to moderate web debates with significantly less effort. Comments are automatically pre-analyzed and filtered using automated learning processes, thus reducing manual moderation effort. Through this semi-automated decision process, media houses and publishers should be able to offer web debates on their own websites again and thus enter into a more active exchange with the readership. The methods and processes used will then be validated in the context of a crowd sourcing study by citizens (future users). In addition, the methods used are always transparently disclosed in order to further strengthen user acceptance. Within the framework of the project, existing expertise in comment moderation will be recorded through qualitative interviews with community managers of the project partners. Thus, domain-specific knowledge can be incorporated into the planned web platform and thus lead to the entire workflow of the software system improvements and a broader acceptance of the users as well as moderators.