MovieTweeters: An Interactive Interface to Improve Recommendation Novelty

Ishan  Ghanmode; Nava Tintarev

MovieTweeters: An Interactive Interface to Improve Recommendation Novelty

Web Information Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

58 Downloads (Pure)

Abstract

This paper introduces and evaluates a novel interface, MovieTweeters. It is a movie recommendation system which incorporates social information with a traditional recommendation algorithm to generate recommendations for users. Few previous studies have investigated the influence of using social information in interactive
interfaces to improve the novelty of recommendations. To address this gap, we investigate whether social information can be incorporated effectively into an interactive interface to improve recommendation novelty and user satisfaction. Our initial results suggest that such an interactive interface does indeed help users discover
more novel items. Also, we observed users who perceived that they discovered more novel and diverse items reported increased levels
of user satisfaction. Surprisingly, we observed that even though we successfully were able to increase the system diversity of the recommendations, it had a negative correlation with users perception of novelty and diversity of the items highlighting the importance of improved user-centered approaches.

Original language	English
Title of host publication	Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems
Editors	Peter Brusilovsky, Marco de Gemmis, Alexander Felfernig, Pasquale Lops, John O'Donovan, Giovanni Semeraro, Martijn C. Willemsen
Publisher	CEUR
Pages	24-31
Number of pages	8
Publication status	Published - 2018
Event	IntRS 2018: 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems - Vancouver, Canada Duration: 7 Oct 2018 → 7 Oct 2018

Publication series

Name	CEUR Workshop Proceedings
Volume	2225
ISSN (Print)	1613-0073

Workshop

Workshop	IntRS 2018
Country/Territory	Canada
City	Vancouver
Period	7/10/18 → 7/10/18

Bibliographical note

Accepted author manuscript

Keywords

Social Recommendation Systems
Novelty
Diversity
User Satisfaction
Interactive User Interfaces

Access to Document

MovieTweetersAccepted author manuscript, 1.18 MB

http://ceur-ws.org/Vol-2225/

Cite this

Ghanmode, I., & Tintarev, N. (2018). MovieTweeters: An Interactive Interface to Improve Recommendation Novelty. In P. Brusilovsky, M. de Gemmis, A. Felfernig, P. Lops, J. O'Donovan, G. Semeraro, & M. C. Willemsen (Eds.), Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (pp. 24-31). (CEUR Workshop Proceedings; Vol. 2225). CEUR. http://ceur-ws.org/Vol-2225/

Ghanmode, Ishan ; Tintarev, Nava. / MovieTweeters : An Interactive Interface to Improve Recommendation Novelty. Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems. editor / Peter Brusilovsky ; Marco de Gemmis ; Alexander Felfernig ; Pasquale Lops ; John O'Donovan ; Giovanni Semeraro ; Martijn C. Willemsen. CEUR, 2018. pp. 24-31 (CEUR Workshop Proceedings).

@inproceedings{efadd033d43342a79fc23f3f913be97c,

title = "MovieTweeters: An Interactive Interface to Improve Recommendation Novelty",

abstract = "This paper introduces and evaluates a novel interface, MovieTweeters. It is a movie recommendation system which incorporates social information with a traditional recommendation algorithm to generate recommendations for users. Few previous studies have investigated the influence of using social information in interactiveinterfaces to improve the novelty of recommendations. To address this gap, we investigate whether social information can be incorporated effectively into an interactive interface to improve recommendation novelty and user satisfaction. Our initial results suggest that such an interactive interface does indeed help users discovermore novel items. Also, we observed users who perceived that they discovered more novel and diverse items reported increased levelsof user satisfaction. Surprisingly, we observed that even though we successfully were able to increase the system diversity of the recommendations, it had a negative correlation with users perception of novelty and diversity of the items highlighting the importance of improved user-centered approaches.",

keywords = "Social Recommendation Systems, Novelty, Diversity, User Satisfaction, Interactive User Interfaces",

author = "Ishan Ghanmode and Nava Tintarev",

note = "Accepted author manuscript; IntRS 2018 : 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems ; Conference date: 07-10-2018 Through 07-10-2018",

year = "2018",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR",

pages = "24--31",

editor = "Brusilovsky, {Peter } and {de Gemmis}, {Marco } and Felfernig, {Alexander } and Lops, {Pasquale } and O'Donovan, {John } and Semeraro, {Giovanni } and Willemsen, {Martijn C.}",

booktitle = "Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems",

}

Ghanmode, I & Tintarev, N 2018, MovieTweeters: An Interactive Interface to Improve Recommendation Novelty. in P Brusilovsky, M de Gemmis, A Felfernig, P Lops, J O'Donovan, G Semeraro & MC Willemsen (eds), Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems. CEUR Workshop Proceedings, vol. 2225, CEUR, pp. 24-31, IntRS 2018, Vancouver, Canada, 7/10/18. <http://ceur-ws.org/Vol-2225/>

MovieTweeters : An Interactive Interface to Improve Recommendation Novelty. / Ghanmode, Ishan ; Tintarev, Nava.

Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems. ed. / Peter Brusilovsky; Marco de Gemmis; Alexander Felfernig; Pasquale Lops; John O'Donovan; Giovanni Semeraro; Martijn C. Willemsen. CEUR, 2018. p. 24-31 (CEUR Workshop Proceedings; Vol. 2225).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - MovieTweeters

T2 - IntRS 2018

AU - Ghanmode, Ishan

AU - Tintarev, Nava

N1 - Accepted author manuscript

PY - 2018

Y1 - 2018

N2 - This paper introduces and evaluates a novel interface, MovieTweeters. It is a movie recommendation system which incorporates social information with a traditional recommendation algorithm to generate recommendations for users. Few previous studies have investigated the influence of using social information in interactiveinterfaces to improve the novelty of recommendations. To address this gap, we investigate whether social information can be incorporated effectively into an interactive interface to improve recommendation novelty and user satisfaction. Our initial results suggest that such an interactive interface does indeed help users discovermore novel items. Also, we observed users who perceived that they discovered more novel and diverse items reported increased levelsof user satisfaction. Surprisingly, we observed that even though we successfully were able to increase the system diversity of the recommendations, it had a negative correlation with users perception of novelty and diversity of the items highlighting the importance of improved user-centered approaches.

AB - This paper introduces and evaluates a novel interface, MovieTweeters. It is a movie recommendation system which incorporates social information with a traditional recommendation algorithm to generate recommendations for users. Few previous studies have investigated the influence of using social information in interactiveinterfaces to improve the novelty of recommendations. To address this gap, we investigate whether social information can be incorporated effectively into an interactive interface to improve recommendation novelty and user satisfaction. Our initial results suggest that such an interactive interface does indeed help users discovermore novel items. Also, we observed users who perceived that they discovered more novel and diverse items reported increased levelsof user satisfaction. Surprisingly, we observed that even though we successfully were able to increase the system diversity of the recommendations, it had a negative correlation with users perception of novelty and diversity of the items highlighting the importance of improved user-centered approaches.

KW - Social Recommendation Systems

KW - Novelty

KW - Diversity

KW - User Satisfaction

KW - Interactive User Interfaces

M3 - Conference contribution

T3 - CEUR Workshop Proceedings

SP - 24

EP - 31

BT - Proceedings of the 5th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems

A2 - Brusilovsky, Peter

A2 - de Gemmis, Marco

A2 - Felfernig, Alexander

A2 - Lops, Pasquale

A2 - O'Donovan, John

A2 - Semeraro, Giovanni

A2 - Willemsen, Martijn C.

PB - CEUR

Y2 - 7 October 2018 through 7 October 2018

ER -

MovieTweeters: An Interactive Interface to Improve Recommendation Novelty

Abstract

Publication series

Workshop

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this