Hygglo

Purpose and goal

Easit wanted to create a system to be able to determine, based on a text, whether it contains gross language and / or other inappropriate content, such as signs of harassment. Within this project, Easit has analyzed, evaluated and implemented solutions around machine learning. As a result of the work in the project, there is now a function in the software Easit GO to detect gross language in incoming emails.

Expected results and effects

The benefit of the solution would be to protect both the sender and the receiver in exchange of information. By notifying a third (educated) person, escalation of bad behavior can be avoided with a safer working environment as a result. Our software has just been released on the market and we have yet to measure its effects. Our knowledge and the organisations overall understanding of machine learning have increased substantially with this project.

Planned approach and implementation

Easit is working in an agile way in iterative sprints. The work is constantly evaluated and adjusted during the progress. The work was divided in four phases; Start-up and analysis, Development, Further development and Evaluation and completion. A big part of the project was spent on analysis and evaluation of different models and approaches. In addition, we have developed a machine learning micros service based on Deeplearning4J as well as end user products.