Online media

STACC is developing a variety of artificial intelligence solutions for companies doing business in the field of online media to enhance business performance and increase competitiveness. Contact us and let’s discuss opportunities for cooperation.

Contact us

RECOMMENDATION SYSTEM FOR IMPROVING USER EXPERIENCE

Every online publication aims to keep the reader on the news site as long as possible and attract him back in the future. This can be achieved by taking the user’s reading experience to a new level with personalized recommendations based on the user’s behavior, that is, recommending news articles specifically relevant to a particular reader.

TEXT ANALYTICS

Various text analytics tools enable to turn text into quantitative data, that is, to change it into a format suitable for calculations. This way, text documents can be quickly searched and analyzed, furthermore, text analytics helps to identify, manage and anonymize personal information, which is necessary in the context of the revised General Data Protection Regulation.

MACHINE LEARNING FEASIBILITY ANALYSIS

Any online newspaper that wants to stand out in the market should consider the implementation of machine learning, because in order to remain competitive, one has to know better and better their customer, make precise management decisions to perform business goals, and ensure the quality of products and services. Machine learning will do all of this for you.

ÄRIPÄEV

A tool for automatically tagging texts – the solution finds automatically tag words for the text, being able to define tag words that don’t appear in the text but are relevant to the content of the text

CV-ONLINE

Recommender system based on text analytics for finding job ads relevant for the job-seeker

INFOREGISTER

Machine learning system that finds out the optimal behavioral pattern by learning from historical data, and gives recommendations on which steps a specialist should take in order to achieve the best possible result

ÕHTULEHT

A tool for automatically assessing the inappropriateness (offensive, racist, violent, etc.) of the content of the comments