Exploring Users' Perception of Collaborative Explanation Styles

被引：5

作者：

Coba, Ludovik ^{[1
]}

Zanker, Markus ^{[1
]}

Rook, Laurens ^{[2
]}

Symeonidis, Panagiotis ^{[1
]}

机构：

[1] Free Univ Bozen Bolzano, Bolzano, Italy

[2] Delft Univ Technol, Delft, Netherlands

来源：

2018 20TH IEEE INTERNATIONAL CONFERENCE ON BUSINESS INFORMATICS (IEEE CBI 2018), VOL 1 | 2018年

关键词：

Recommender Systems; Collaborative Filtering; Explanations; Conjoint Experiment; DISCRETE-CHOICE EXPERIMENTS; TAXONOMY;

D O I：

10.1109/CBI.2018.00017

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.

引用

页码：70 / 78

页数：9

共 33 条

[1] Using Explainability for Constrained Matrix Factorization
Abdollahi, Behnoush
Nasraoui, Olfa
[J]. PROCEEDINGS OF THE ELEVENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'17), 2017, : 79 - 83
[2] [Anonymous], 2003, Proceedings of CHI 2003: Human Factorsin Computing Systems
[3] [Anonymous], 2014, JOINT WORKSHOP INTER
[4] Bilgic M., P PERS 2005 WORKSH N, P13
[5] Social Network Sites: Definition, History, and Scholarship
Boyd, Danah M.
Ellison, Nicole B.
[J]. JOURNAL OF COMPUTER-MEDIATED COMMUNICATION, 2007, 13 (01): : 210 - 230
[6] Choosing a Physician on Social Media: Comments and Ratings of Users are More Important than the Qualification of a Physician
Carbonell, Guillermo
Brand, Matthias
[J]. INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION, 2018, 34 (02) : 117 - 128
[7] Human Decision Making and Recommender Systems
Chen, Li
de Gemmis, Marco
Felfernig, Alexander
Lops, Pasquale
Ricci, Francesco
Semeraro, Giovanni
[J]. ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, 2013, 3 (03)
[8] Cho M., 2015, P 33 ANN ACM C EXT A, P899
[9] Chu W, 2009, KDD-09: 15TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, P1097
[10] Coba L., 2018, DECISION MAKING MAXI

← 1 2 3 4 →