For more than a decade already, there has been an enormous growth of social networks and their audiences. As people post about their life and experiences, comment on other people's posts and discuss all sorts of topics, they generate a tremendous amount of data that are stored in these networks. It is virtually impossible for a user to get a concise overview about any given topic.

Project Socneto offers a framework allowing the users to analyze data related to a chosen topic from given social networks. Generally, a user specifes a topic of interest, selects type(s) of required analyses and social networks to be used as data sources. Socneto then starts collecting respective data, runs them through analyzers and stores the results. The user can then see the results either in a tabular version or visualized with customized charts.

A typical use case is studying sentiment about a public topic (e.g., traffc, medicine etc.) after an important press conference, tracking the opinion evolution about a new product on the market, or comparing stock market values and the general public sentiment peaks of a company of interest.


Name Responsibilities
Petra Vysušilová Machine learning, linguistic specialist -develops the sentiment analysis model
Jaroslav Knotek Software engineer - designs and builds the platform
Lukáš Kolek Data engineer - designs and develops the data storage
Jůlius Flimmel Web engineer - builds the web application and front end


Socneto consists from four parts:


Technically skilled user can extend the application by listening to a specific channel.

All components run in docker.

More Information

For more information refer to the user and development documentation. The source codes can be found in the GitHub repository.

The results of the project have been published in paper: Knotek, J. - Kolek, L. - Vysusilova, P. - Flimmel, J. - Holubova, I.: Socneto: a Scent of Current Network Overview. RCIS '21: Proceedings of the 15th International Conference on Research Challenges in Information Science, pages 568 - 574, May 2021. Lecture Notes in Computer Science, Springer 2021. ISBN 978-3-030-75017-6. [www, presentation]