Using Audio-Derived Affective Offset to Enhance TV Recommendation

Sven Ewan Shepstone, Zheng-Hua Tan, Søren Holdt Jensen

Research output: Contribution to journalJournal articleResearchpeer-review

13 Citations (Scopus)

Abstract

This paper introduces the concept of affective offset, which is the difference between a user's perceived affective state and the affective annotation of the content they wish to see. We show how this affective offset can be used within a framework for providing recommendations for TV programs. First a user's mood profile is determined using 12-class audio-based emotion classifications . An initial TV content item is then displayed to the user based on the extracted mood profile. The user has the option to either accept the recommendation, or to critique the item once or several times, by navigating the emotion space to request an alternative match. The final match is then compared to the initial match, in terms of the difference in the items' affective parameterization . This offset is then utilized in future recommendation sessions. The system was evaluated by eliciting three different moods in 22 separate users and examining the influence of applying affective offset to the users' sessions. Results show that, in the case when affective offset was applied, better user satisfaction was achieved: the average ratings went from 7.80 up to 8.65, with an average decrease in the number of critiquing cycles which went from 29.53 down to 14.39.
Original languageEnglish
JournalI E E E Transactions on Multimedia
Volume16
Issue number7
Pages (from-to)1999-2010
Number of pages12
ISSN1520-9210
DOIs
Publication statusPublished - 10 Jul 2014

Fingerprint

Parameterization

Cite this

@article{076db9b53353437da52a9c691ff204c0,
title = "Using Audio-Derived Affective Offset to Enhance TV Recommendation",
abstract = "This paper introduces the concept of affective offset, which is the difference between a user's perceived affective state and the affective annotation of the content they wish to see. We show how this affective offset can be used within a framework for providing recommendations for TV programs. First a user's mood profile is determined using 12-class audio-based emotion classifications . An initial TV content item is then displayed to the user based on the extracted mood profile. The user has the option to either accept the recommendation, or to critique the item once or several times, by navigating the emotion space to request an alternative match. The final match is then compared to the initial match, in terms of the difference in the items' affective parameterization . This offset is then utilized in future recommendation sessions. The system was evaluated by eliciting three different moods in 22 separate users and examining the influence of applying affective offset to the users' sessions. Results show that, in the case when affective offset was applied, better user satisfaction was achieved: the average ratings went from 7.80 up to 8.65, with an average decrease in the number of critiquing cycles which went from 29.53 down to 14.39.",
author = "Shepstone, {Sven Ewan} and Zheng-Hua Tan and Jensen, {S{\o}ren Holdt}",
year = "2014",
month = "7",
day = "10",
doi = "10.1109/TMM.2014.2337845",
language = "English",
volume = "16",
pages = "1999--2010",
journal = "I E E E Transactions on Multimedia",
issn = "1520-9210",
publisher = "IEEE",
number = "7",

}

Using Audio-Derived Affective Offset to Enhance TV Recommendation. / Shepstone, Sven Ewan; Tan, Zheng-Hua; Jensen, Søren Holdt.

In: I E E E Transactions on Multimedia, Vol. 16, No. 7, 10.07.2014, p. 1999-2010.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Using Audio-Derived Affective Offset to Enhance TV Recommendation

AU - Shepstone, Sven Ewan

AU - Tan, Zheng-Hua

AU - Jensen, Søren Holdt

PY - 2014/7/10

Y1 - 2014/7/10

N2 - This paper introduces the concept of affective offset, which is the difference between a user's perceived affective state and the affective annotation of the content they wish to see. We show how this affective offset can be used within a framework for providing recommendations for TV programs. First a user's mood profile is determined using 12-class audio-based emotion classifications . An initial TV content item is then displayed to the user based on the extracted mood profile. The user has the option to either accept the recommendation, or to critique the item once or several times, by navigating the emotion space to request an alternative match. The final match is then compared to the initial match, in terms of the difference in the items' affective parameterization . This offset is then utilized in future recommendation sessions. The system was evaluated by eliciting three different moods in 22 separate users and examining the influence of applying affective offset to the users' sessions. Results show that, in the case when affective offset was applied, better user satisfaction was achieved: the average ratings went from 7.80 up to 8.65, with an average decrease in the number of critiquing cycles which went from 29.53 down to 14.39.

AB - This paper introduces the concept of affective offset, which is the difference between a user's perceived affective state and the affective annotation of the content they wish to see. We show how this affective offset can be used within a framework for providing recommendations for TV programs. First a user's mood profile is determined using 12-class audio-based emotion classifications . An initial TV content item is then displayed to the user based on the extracted mood profile. The user has the option to either accept the recommendation, or to critique the item once or several times, by navigating the emotion space to request an alternative match. The final match is then compared to the initial match, in terms of the difference in the items' affective parameterization . This offset is then utilized in future recommendation sessions. The system was evaluated by eliciting three different moods in 22 separate users and examining the influence of applying affective offset to the users' sessions. Results show that, in the case when affective offset was applied, better user satisfaction was achieved: the average ratings went from 7.80 up to 8.65, with an average decrease in the number of critiquing cycles which went from 29.53 down to 14.39.

U2 - 10.1109/TMM.2014.2337845

DO - 10.1109/TMM.2014.2337845

M3 - Journal article

VL - 16

SP - 1999

EP - 2010

JO - I E E E Transactions on Multimedia

JF - I E E E Transactions on Multimedia

SN - 1520-9210

IS - 7

ER -