Standard

Towards Analogy-based Recommendation : Benchmarking of Perceived Analogy Semantics. / Lofi, Christoph; Tintarev, Nava.

ComplexRec 2017 Recommendation in Complex Scenarios: Proceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios. ed. / T. Bogers; M. Koolen; B. Mobasher; A. Said; A. Tuzhilin. CEUR-WS, 2017. p. 9-13 (Ceur Workshop Proceedings; Vol. 1892).

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Harvard

Lofi, C & Tintarev, N 2017, Towards Analogy-based Recommendation: Benchmarking of Perceived Analogy Semantics. in T Bogers, M Koolen, B Mobasher, A Said & A Tuzhilin (eds), ComplexRec 2017 Recommendation in Complex Scenarios: Proceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios. Ceur Workshop Proceedings, vol. 1892, CEUR-WS, pp. 9-13, RecSys 2017 Workshop on Recommendation in Complex Scenarios, Como, Italy, 31/08/17.

APA

Lofi, C., & Tintarev, N. (2017). Towards Analogy-based Recommendation: Benchmarking of Perceived Analogy Semantics. In T. Bogers, M. Koolen, B. Mobasher, A. Said, & A. Tuzhilin (Eds.), ComplexRec 2017 Recommendation in Complex Scenarios: Proceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios (pp. 9-13). (Ceur Workshop Proceedings; Vol. 1892). CEUR-WS.

Vancouver

Lofi C, Tintarev N. Towards Analogy-based Recommendation: Benchmarking of Perceived Analogy Semantics. In Bogers T, Koolen M, Mobasher B, Said A, Tuzhilin A, editors, ComplexRec 2017 Recommendation in Complex Scenarios: Proceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios. CEUR-WS. 2017. p. 9-13. (Ceur Workshop Proceedings).

Author

Lofi, Christoph ; Tintarev, Nava. / Towards Analogy-based Recommendation : Benchmarking of Perceived Analogy Semantics. ComplexRec 2017 Recommendation in Complex Scenarios: Proceedings of the RecSys 2017 Workshop on Recommendation in Complex Scenarios. editor / T. Bogers ; M. Koolen ; B. Mobasher ; A. Said ; A. Tuzhilin. CEUR-WS, 2017. pp. 9-13 (Ceur Workshop Proceedings).

BibTeX

@inproceedings{5581c974167b49298f8403b8ee56a7a3,
title = "Towards Analogy-based Recommendation: Benchmarking of Perceived Analogy Semantics",
abstract = "Requests for recommendation can be seen as a form of query for candidate items, ranked by relevance. Users are however o‰enunable to crisply de€ne what they are looking for. One of the core concepts of natural communication for describing and explainingcomplex information needs in an intuitive fashion are analogies: e.g., “What is to Christopher Nolan as is 2001: A Space Odyssey toStanley Kubrick?”. Analogies allow users to explore the item space by formulating queries in terms of items rather than explicitlyspecifying the properties that they €nd aŠractive. One of the core challenges which hamper research on analogy-enabled queries isthat 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.",
keywords = "Analogy-Enabled Recommendation, Relational Similarity, Analogy Benchmarking",
author = "Christoph Lofi and Nava Tintarev",
year = "2017",
language = "English",
series = "Ceur Workshop Proceedings",
publisher = "CEUR-WS",
pages = "9--13",
editor = "T. Bogers and M. Koolen and B. Mobasher and A. Said and A. Tuzhilin",
booktitle = "ComplexRec 2017 Recommendation in Complex Scenarios",

}

RIS

TY - GEN

T1 - Towards Analogy-based Recommendation

T2 - Benchmarking of Perceived Analogy Semantics

AU - Lofi, Christoph

AU - Tintarev, Nava

PY - 2017

Y1 - 2017

N2 - Requests for recommendation can be seen as a form of query for candidate items, ranked by relevance. Users are however o‰enunable to crisply de€ne what they are looking for. One of the core concepts of natural communication for describing and explainingcomplex information needs in an intuitive fashion are analogies: e.g., “What is to Christopher Nolan as is 2001: A Space Odyssey toStanley Kubrick?”. Analogies allow users to explore the item space by formulating queries in terms of items rather than explicitlyspecifying the properties that they €nd aŠractive. One of the core challenges which hamper research on analogy-enabled queries isthat 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.

AB - Requests for recommendation can be seen as a form of query for candidate items, ranked by relevance. Users are however o‰enunable to crisply de€ne what they are looking for. One of the core concepts of natural communication for describing and explainingcomplex information needs in an intuitive fashion are analogies: e.g., “What is to Christopher Nolan as is 2001: A Space Odyssey toStanley Kubrick?”. Analogies allow users to explore the item space by formulating queries in terms of items rather than explicitlyspecifying the properties that they €nd aŠractive. One of the core challenges which hamper research on analogy-enabled queries isthat 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.

KW - Analogy-Enabled Recommendation

KW - Relational Similarity

KW - Analogy Benchmarking

UR - http://ceur-ws.org/Vol-1892/

UR - http://resolver.tudelft.nl/uuid:5581c974-167b-4929-8f84-03b8ee56a7a3

M3 - Conference contribution

T3 - Ceur Workshop Proceedings

SP - 9

EP - 13

BT - ComplexRec 2017 Recommendation in Complex Scenarios

A2 - Bogers, T.

A2 - Koolen, M.

A2 - Mobasher, B.

A2 - Said, A.

A2 - Tuzhilin, A.

PB - CEUR-WS

ER -

ID: 32310935