EventAdvisor

The EventAdvisor is a semantic matchmaking tool that connects you with talks, attendees, and job positions that are most relevant to you. With its innovative and powerful knowledge model, the EventAdvisor extracts keywords from your profile to find matches.
For quality matches and to ensure you get great results, be sure to create your own profile by uploading your CV, connecting to LinkedIn or adding keywords, as well as writing about yourself.
Create your own search filter by simply adding keywords about skills, topics and job positions that are relevant to you.
Please note that the EventAdvisor only works in English.

Matchmaker

The Matchmaker helps you find the most relevant talks and attendees based on your profile. Keywords from you profile generate a semantic Footprint, helping the Matchmaker find the most relevant talks and attendees based on your profile. For best results, make sure to complete your profile by uploading your CV, connecting to LinkedIn, adding keywords and writing about yourself.

Your Search Filters

Leverage the Matchmaker's usability by creating your own customized search and saving it for future use.
A customized search filter allows you to:

  • Choose between only attendees or talks (or both)
  • Add keywords about skills, topics and job positions that you are interested in
  • Upload your personal semantic Footprint and adapt it to the specific needs of your search.

Job Offers

Participating in the Job Fair allows you to see matching job offers from our sponsors and partners. In turn, if there is a match, sponsors and partners of SEMANTiCS 2018 will be able to see your profile.
Similar to the Matchmaker,  your personal profile provides the basis of your matches.

Knowledge model

The core functionality of the EventAdvisor comes from a powerful knowledge model, containing a triple store database with skills, topics, occupations, and industries. The knowledge model also contains information about industries extracted from the LinkedIn Industry classification. Information regarding industries is not used for the matchmaking process. The knowledge model has been built with PoolParty and contains over 21,000 concepts.

The EventAdvisor uses an adapted and enhanced version of the ESCO classification of the European Commission as a basis for skills and the occupations that are related to them.

Method

The matchmaking process:

  1. A semantic Footprint is generated from the user profile data (and the connected talk in case of presenters). The Footprint contains concepts that have been extracted from the EventAdvisor knowledge graph. The data and the Footprint are stored in Drupal and the PoolParty GraphSearch index.
  2. In order to find suitable matches, the Footprint is enriched with further information from the knowledge graph. Not only are exact matches from the Footprint used, but also related concepts, siblings, broader and narrower concepts. Most importantly skills are enriched with relevant job positions on the basis of the ESCO classification, and vice versa. Each type of match is scored differently, which is then used to calculate the overall score of an extracted concept. The result of this process is a vector with the extracted concepts and their scores.
  3. This vector is used to find matching attendees, talks and job positions in our Solr index. Solr calculates the scores of the matches (the closer the match, the higher the score) and sorts them. The result is a sorted list of attendees, talks, and job positions.
  4. The result list is then displayed in the EventAdvisor app in Drupal.

In the case of personalized search filters, the search terms correspond to concepts found in the knowledge graph. The search parameters are only stored when the user wants to save a filter for future use. The search results are calculated again each time you use a search filter. The search can be faceted by attendees and talks.

Team

Juliane Pineiro-Winkler, Kurt Moser, Susan Haertig