Defining and Supporting Narrative-driven Recommendation

Toine Bogers, Marijn Koolen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

28 Citations (Scopus)
7 Downloads (Pure)

Abstract

Research into recommendation algorithms has made great strides in recent years. However, these algorithms are typically applied in relatively straightforward scenarios: given information about a user's past preferences, what will they like in the future? Recommendation is often more complex: evaluating recommended items never takes place in a vacuum, and it is often a single step in the user's more complex background task. In this paper, we define a specific type of recommendation scenario called narrative-driven recommendation, where the recommendation process is driven by both a log of the user's past transactions as well as a narrative description of their current interest(s). Through an analysis of a set of real-world recommendation narratives from the LibraryThing forums, we demonstrate the uniqueness and richness of this scenario and highlight common patterns and properties of such narratives.
Original languageEnglish
Title of host publicationProceedings of the Eleventh ACM Conference on Recommender Systems : RecSys '17
Number of pages5
PublisherAssociation for Computing Machinery (ACM)
Publication date27 Aug 2017
Pages238-242
ISBN (Electronic)978-1-4503-4652-8
DOIs
Publication statusPublished - 27 Aug 2017
EventRecSys 2017: 11th ACM Conference on Recommender Systems - Como, Italy, Como, Italy
Duration: 27 Aug 201731 Aug 2017
Conference number: 11
https://recsys.acm.org/recsys17/

Conference

ConferenceRecSys 2017: 11th ACM Conference on Recommender Systems
Number11
LocationComo, Italy
Country/TerritoryItaly
CityComo
Period27/08/201731/08/2017
Internet address

Keywords

  • narrative-driven recommendation
  • query-driven recommendation
  • complex recommendation
  • conversational recommenders

Fingerprint

Dive into the research topics of 'Defining and Supporting Narrative-driven Recommendation'. Together they form a unique fingerprint.

Cite this