Summary of the project

The magnet project is developing a software platform to support journalists in the early phase of an article production by automatically resurfacing older content from previous articles, relevant for the current moment.
To reach this objective, the intelligence of the platform is twofold: It is capable of understanding the topic of the activity being developed by the journalist; and, it prioritises content that has a similar context with the current situation being handled. The similarity of context is strongly derived by the activities developed by other journalists, giving a strong emphasis on aspects of collaborative filtering. Topic and context identification are the two vehicles enabling the platform to automatically recommend older content in the media archives, and timely offer it to the journalists.
The competition with social networks puts a pressure to accelerate the news production. There is gradually less time to verify sources and control the journalistic process. Thus, journalists need supporting tools helping them to co-create news content, namely, to access the relevant knowledge in between the large quantity of articles stored in an ever-growing news archive. Intelligently accessing selected items of previous news and other information items in the related topic and in context, allows the journalist to have a clearer picture and understand which are the deciding issues that should be more investigated, therefore boosting their productivity (while reducing the level of non-intentional disinformation). This is what the magnet project aims to purvey to workers from the media industry.
A key innovation aspect of magnet project is the context-based search on top of the topic-oriented approach. The platform uses algorithms based on Vector Space Models and Context Modelling, contributing to both the transparency and explainability of the proposed solution, as this is a very important aspect regarding the journalistic activity.

The team: