Comparative analysis of relevance feedback methods based on two user studies

Stephen Akuma, Rahat Iqbal, Chrisina Jayne, Faiyaz Doctor

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Rigorous analysis of user interest in web documents is essential for the development of recommender systems. This paper investigates the relationship between the implicit parameters and user explicit rating during their search and reading tasks. The objective of this paper is therefore three-fold: firstly, the paper identifies the implicit parameters which are statistically correlated with the user explicit rating through user study 1. These parameters are used to develop a predictive model which can be used to represent users’ perceived relevance of documents. Secondly, it investigates the reliability and validity of the predictive model by comparing it with eye gaze during a reading task through user study 2. Our findings suggest that there is no significant difference between the predictive model based on implicit indicators and eye gaze within the context examined. Thirdly, we measured the consistency of user explicit rating in both studies and found significant consistency in user explicit rating of document relevance and interest level which further validates the predictive model. We envisage that the results presented in this paper can help to develop recommender and personalised systems for recommending documents to users based on their previous interaction with the system.
Original languageEnglish
Pages (from-to)138-146
JournalComputers in Human Behavior
Volume60
Early online date27 Feb 2016
DOIs
Publication statusPublished - Jul 2016

Fingerprint

Reading
Feedback
Reproducibility of Results
Recommender systems
User Studies
Comparative Analysis
Rating

Bibliographical note

The full text is currently unavailable on the repository.

Keywords

  • Implicit feedback
  • User interest
  • Explicit feedback
  • Implicit indicators
  • Explicit rating
  • Recommender system

Cite this

Comparative analysis of relevance feedback methods based on two user studies. / Akuma, Stephen; Iqbal, Rahat; Jayne, Chrisina; Doctor, Faiyaz.

In: Computers in Human Behavior, Vol. 60, 07.2016, p. 138-146.

Research output: Contribution to journalArticle

Akuma, Stephen ; Iqbal, Rahat ; Jayne, Chrisina ; Doctor, Faiyaz. / Comparative analysis of relevance feedback methods based on two user studies. In: Computers in Human Behavior. 2016 ; Vol. 60. pp. 138-146.
@article{eccc130e72604186900f81fcc907edbf,
title = "Comparative analysis of relevance feedback methods based on two user studies",
abstract = "Rigorous analysis of user interest in web documents is essential for the development of recommender systems. This paper investigates the relationship between the implicit parameters and user explicit rating during their search and reading tasks. The objective of this paper is therefore three-fold: firstly, the paper identifies the implicit parameters which are statistically correlated with the user explicit rating through user study 1. These parameters are used to develop a predictive model which can be used to represent users’ perceived relevance of documents. Secondly, it investigates the reliability and validity of the predictive model by comparing it with eye gaze during a reading task through user study 2. Our findings suggest that there is no significant difference between the predictive model based on implicit indicators and eye gaze within the context examined. Thirdly, we measured the consistency of user explicit rating in both studies and found significant consistency in user explicit rating of document relevance and interest level which further validates the predictive model. We envisage that the results presented in this paper can help to develop recommender and personalised systems for recommending documents to users based on their previous interaction with the system.",
keywords = "Implicit feedback, User interest, Explicit feedback, Implicit indicators, Explicit rating, Recommender system",
author = "Stephen Akuma and Rahat Iqbal and Chrisina Jayne and Faiyaz Doctor",
note = "The full text is currently unavailable on the repository.",
year = "2016",
month = "7",
doi = "10.1016/j.chb.2016.02.064",
language = "English",
volume = "60",
pages = "138--146",
journal = "Computers in Human Behavior",
issn = "0747-5632",
publisher = "Elsevier",

}

TY - JOUR

T1 - Comparative analysis of relevance feedback methods based on two user studies

AU - Akuma, Stephen

AU - Iqbal, Rahat

AU - Jayne, Chrisina

AU - Doctor, Faiyaz

N1 - The full text is currently unavailable on the repository.

PY - 2016/7

Y1 - 2016/7

N2 - Rigorous analysis of user interest in web documents is essential for the development of recommender systems. This paper investigates the relationship between the implicit parameters and user explicit rating during their search and reading tasks. The objective of this paper is therefore three-fold: firstly, the paper identifies the implicit parameters which are statistically correlated with the user explicit rating through user study 1. These parameters are used to develop a predictive model which can be used to represent users’ perceived relevance of documents. Secondly, it investigates the reliability and validity of the predictive model by comparing it with eye gaze during a reading task through user study 2. Our findings suggest that there is no significant difference between the predictive model based on implicit indicators and eye gaze within the context examined. Thirdly, we measured the consistency of user explicit rating in both studies and found significant consistency in user explicit rating of document relevance and interest level which further validates the predictive model. We envisage that the results presented in this paper can help to develop recommender and personalised systems for recommending documents to users based on their previous interaction with the system.

AB - Rigorous analysis of user interest in web documents is essential for the development of recommender systems. This paper investigates the relationship between the implicit parameters and user explicit rating during their search and reading tasks. The objective of this paper is therefore three-fold: firstly, the paper identifies the implicit parameters which are statistically correlated with the user explicit rating through user study 1. These parameters are used to develop a predictive model which can be used to represent users’ perceived relevance of documents. Secondly, it investigates the reliability and validity of the predictive model by comparing it with eye gaze during a reading task through user study 2. Our findings suggest that there is no significant difference between the predictive model based on implicit indicators and eye gaze within the context examined. Thirdly, we measured the consistency of user explicit rating in both studies and found significant consistency in user explicit rating of document relevance and interest level which further validates the predictive model. We envisage that the results presented in this paper can help to develop recommender and personalised systems for recommending documents to users based on their previous interaction with the system.

KW - Implicit feedback

KW - User interest

KW - Explicit feedback

KW - Implicit indicators

KW - Explicit rating

KW - Recommender system

U2 - 10.1016/j.chb.2016.02.064

DO - 10.1016/j.chb.2016.02.064

M3 - Article

VL - 60

SP - 138

EP - 146

JO - Computers in Human Behavior

JF - Computers in Human Behavior

SN - 0747-5632

ER -