Documents

  • paper2

    Final published version, 437 KB, PDF-document

Links

Requests for recommendation can be seen as a form of query for candidate items, ranked by relevance. Users are however o‰en
unable to crisply de€ne what they are looking for. One of the core concepts of natural communication for describing and explaining
complex information needs in an intuitive fashion are analogies: e.g., “What is to Christopher Nolan as is 2001: A Space Odyssey to
Stanley Kubrick?”. Analogies allow users to explore the item space by formulating queries in terms of items rather than explicitly
specifying the properties that they €nd aŠractive. One of the core challenges which hamper research on analogy-enabled queries is
that analogy semantics rely on consensus on human perception, which is not well represented in current benchmark data sets. Œerefore, in this paper we introduce a new benchmark dataset focusing on the human aspects for analogy semantics. Furthermore, we evaluate a popular technique for analogy semantics (word2vec neuronal embeddings) using our dataset. Œe results show that current word embedding approaches are still not not suitable to su�ciently deal with deeper analogy semantics. We discuss future directions including hybrid algorithms also incorporating structural or crowd-based approaches, and the potential for analogy-based explanations.
Original languageEnglish
Title of host publicationComplexRec 2017 Recommendation in Complex Scenarios
Subtitle of host publicationProceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios
EditorsT. Bogers, M. Koolen, B. Mobasher, A. Said, A. Tuzhilin
PublisherCEUR-WS
Pages9-13
Number of pages5
StatePublished - 2017
EventRecSys 2017 Workshop on Recommendation in Complex Scenarios - Como, Italy
Duration: 31 Aug 201731 Aug 2017

Publication series

NameCeur Workshop Proceedings
PublisherCEUR
Volume1892
ISSN (Electronic)1613-0073

Workshop

WorkshopRecSys 2017 Workshop on Recommendation in Complex Scenarios
CountryItaly
CityComo
Period31/08/1731/08/17

    Research areas

  • Analogy-Enabled Recommendation, Relational Similarity, Analogy Benchmarking

ID: 32310935