ExpLOD: a Framework for Explaining Recommendations based on the Linked Open Data Cloud

被引：40

作者：

Musto, Cataldo ^{[1
]}

Narducci, Fedelucio ^{[1
]}

Lops, Pasquale ^{[1
]}

De Gemmis, Marco ^{[1
]}

Semeraro, Giovanni ^{[1
]}

机构：

[1] Univ Bari Aldo Moro, Dept Comp Sci, Bari, Italy

来源：

PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16) | 2016年

关键词：

D O I：

10.1145/2959100.2959173

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we present ExPLOD, a framework which exploits the information available in the Linked Open Data (LOD) cloud to generate a natural language explanation of the suggestions produced by a recommendation algorithm. The methodology is based on building a graph in which the items liked by a user are connected to the items recommended through the properties available in the LOD cloud. Next, given this graph, we implemented some techniques to rank those properties and we used the most relevant ones to feed a module for generating explanations in natural language. In the experimental evaluation we performed a user study with 308 subjects aiming to investigate to what extent our explanation framework can lead to more transparent, trustful and engaging recommendations. The preliminary results provided us with encouraging findings, since our algorithm performed better than both a non-personalized explanation baseline and a popularity-based one.

引用

页码：151 / 154

页数：4

共 8 条

[1]

Bilgic M., 2005, PERSONALIZATION IUI, V5

[2]

Carenini G., 2001, P 17 INT JOINT C ART, P1307

[3] Topic-sensitive PageRank: A context-sensitive ranking algorithm for Web search [J].

Haveliwala, TH .

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2003, 15 (04) :784-796

[4]

Herlocker J. L., 2000, P 2000 ACM C COMP SU, P241, DOI DOI 10.1145/358916.358995

[5]

Knijnenburg B.P., 2015, Recommender Systems Handbook, P309, DOI [10.1007/978-0-387-85820-3, DOI 10.1007/978-1-4899-7637-6_9]

[6]

Knijnenburg B. P., 2012, P 6 ACM C REC SYST, P43, DOI [10.1145/2365952.2365966, DOI 10.1145/2365952.2365966]

[7] Introduction to Information Retrieval [J].

Sanderson, Mark .

NATURAL LANGUAGE ENGINEERING, 2010, 16 :100-103

[8] Evaluating the effectiveness of explanations for recommender systems Methodological issues and empirical studies on the impact of personalization [J].

Tintarev, Nava ;

Masthoff, Judith .

USER MODELING AND USER-ADAPTED INTERACTION, 2012, 22 (4-5) :399-439

← 1 →