Personalized Search
This work addresses the challenge of information overload for users of scientific publication databases, though it appears incremental as it builds on existing search engines with a new re-ranking system.
The authors tackled the problem of finding relevant items in large scientific publication databases by developing a personalized search approach that re-ranks results from existing search engines. Their experiments on the CERN Document Server showed that personalized search outperformed baseline methods (latest first and word similarity) in terms of click position in search results.
As the volume of electronically available information grows, relevant items become harder to find. This work presents an approach to personalizing search results in scientific publication databases. This work focuses on re-ranking search results from existing search engines like Solr or ElasticSearch. This work also includes the development of Obelix, a new recommendation system used to re-rank search results. The project was proposed and performed at CERN, using the scientific publications available on the CERN Document Server (CDS). This work experiments with re-ranking using offline and online evaluation of users and documents in CDS. The experiments conclude that the personalized search result outperform both latest first and word similarity in terms of click position in the search result for global search in CDS.