Semantic analysis

Sometimes just tracking user behaviour is not enough. When it comes to large data volumes it might also be interesting to take a look at how text and descriptions are structured. In some cases we combine semantic and behaviour based algorithms to get the best results.

Some of the techniques we use are:

  • Extracting entities like names, places and companies from text
  • Find keyword in texts
  • Search with relevancy expansion (find relevant texts which might not include the exact word, but rather some familiar word)
  • Find how closely texts are related
  • Discover how texts refer to each other and contribute to textual networks
  • Sematic analysis
  • Clustering of texts or products, based on text