• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Software Support

 


1. TopicMiner


Interface software for topic modeling and a visual analysis of the results.
Programming language: C++, Delphi 7, and CUDA.
Development time: 09.2012 - to present
Developers: S. Koltsov and V. Filippov.

Options:
  • Data uploading from BlogMiner and text files;
  • Data parsing;
  • Lemmatization via Mystem (Yandex);
  • Word frequency calculation, creating stop word lists, and deleting stop words according to the word list and frequencies;
  • Topic modeling: LDA with Gibbs Sampling;
  • Recurrent topic modeling;
  • Browsing summary matrices of words and texts on topics, and matrix sorting;
  • Quality calculation and visualization (perplexity);
  • Uploading results in a CSV file;
  • Calculation of average intervals among words in a given word combination and documents.
 
Expected: a topic comparison based on Kullback-Leibler divergence.
 
Download: 

 TopicMiner_LINIS (RAR, 19.47 Mb)



2. BlogMiner


An information system interface for working with the blog platform LiveJournal
Programming language: Delphi 7
Development time: 06.2011 - 01.2013 
Developers: S. Koltsov and R. Bachmudov

Options:
  • Downloading full-text data from the social network LiveJournal (posts, correlated to authors and dates; comments, correlated to posts, commentators, and dates);
  • Data parsing;
  • Storage of LiveJournal data in a set of relational tables on an MS SQL Server;
  • Data backup and recovery;
  • Navigation through raw and parse data;
  • Key word search system based on the Full-Text Search Engine (MS SQL);
  • Data uploading for third-party software (gCluto, Stanford Topic Modeling Toolbox, NodeXL,and TopicMiner);
  • Construction of text and network uploads via SQL requests.
 
Expected: parsing of authors’ metadata.
 

3. VKMiner (Social Network)


Download VKMiner_2017
An information system interface for working with the social network ‘Vkontakte’
Programming language: Delphi XE2 and SQL
Development time: 02.2013 – present
Developers: S. Koltsov and V. Filippov.

Options:
  • Uploading a user’s personal data based on a given ID;
  • Uploading a user’s friends list, and ego network calculation;
  • Uploading a user’s group lists;
  • Uploading lists of group members in ‘Vkontakte’ based on a group ID (with users’ metadata);
  • Uploading friends lists of group members, and friendship network calculation;
  • Full-text uploading of a group wall (posts, correlated to authors and dates; comments, correlated to posts, commentators, and dates; ‘likes’, correlated to authors, posts, and comments);
  • Storing data in relational tables on an MS SQL Server;
  • Uploading results in a CSV file.
 
Expected: a calculation of network liking and commenting by groups; full-text uploading of group discussions.

4. Scripts and single-task software without the interface: about 20.


5. Third-party software applied in the Laboratory for Internet Studies

 
For the terms and conditions of using the databases and software products developed in the Lab, please contact linis-spb@hse.ru.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!