A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

Kavu, Tatenda Duncan; Dube, Kuda; Raeth, Peter G.; Hapanyengwi, Gilford

doi:10.4018/ijictrame.2017010101

Cited by 5 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) isActive (2) INPUT: u (profile of user) (3) i (item or set of items) (4) OUTPUT: bool (True or False) (5) Begin (6) isActive ⟵ False 7ACTIONS ⟵ {click, search, rate, bought} (8) A ⟵ {x: x is recent action on i by u AND x ∈ ACTIONS} (9) if (A ≠ ∅)): (10) isActive ⟵ True (11) return isActive (12) End ALGORITHM 5: isActive.…”

Section: Definition Of Termsmentioning

confidence: 99%

“…return k (8) End ALGORITHM 6: JaccardSimilarity. k ⟵ 0.25;(support threshold) (8) I m ⟵ {X: X ∈ I AND isActive(M, X) ∀ X} (9) FrequentSets ⟵ {X: Support (X, |Im|)>�k, XIm} (10) F ⟵ {i: i ∈ X, X ∈ FrequentSets,∀X} (11) return F (12) End ALGORITHM 7: Apriori. 8 Mathematical Problems in Engineering implements the ID 3 decision tree.…”

Section: Definition Of Termsmentioning

confidence: 99%

“…To address the identified challenges, an investigation was carried out and it was found that recommender algorithms are biased significantly towards system-centric factors such as accuracy, diversity, and scalability [9]. ere is a lack of incorporation of knowledge from these user-centric factors (user experience, user decision-making processes, and user interaction) [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Holistic User Context-Aware Recommender Algorithm

Kavu

Dube

Raeth

2019

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Existing recommender algorithms lack dynamism, human focus, and serendipitous recommendations. The literature indicates that the context of a user influences user decisions, and when incorporated in recommender systems (RSs), novel and serendipitous recommendations can be realized. This article shows that social, cultural, psychological, and economic contexts of a user influence user traits or decisions. The article demonstrates a novel approach of incorporating holistic user context-aware knowledge in an algorithm to solve the highlighted problems. Web content mining and collaborative filtering approaches were used to develop a holistic user context-aware (HUC) algorithm. The algorithm was evaluated on a social network using online experimental evaluations. The algorithm demonstrated dynamism, novelty, and serendipity with an average of 84% novelty and 85% serendipity.

show abstract

Section: Definition Of Termsmentioning

confidence: 99%

Section: Definition Of Termsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Holistic User Context-Aware Recommender Algorithm

Kavu

Dube

Raeth

2019

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…They merely depend on users' actions to predict preferences. Yet recent research exposes the advantages of opening the black box in order to know the changes of user preferences [7], [8]. Previous researches reveal that it might be impossible to offer accurate recommendations without considering user actions.…”

Section: Related Workmentioning

confidence: 99%

“…Previous researches reveal that it might be impossible to offer accurate recommendations without considering user actions. A previous investigation done by [7] implies that a holistic approach that considers user actions together with detailed information from the user can give better recommendations. In this way, recommendations should be more accurate and can cope with evolving preference changes.…”

Section: Related Workmentioning

confidence: 99%

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Kavu¹,

Dube²,

Raeth³

et al. 2018

Proceedings of the EAI International Conference for Research, Innovation and Development for Africa

View full text Add to dashboard Cite

Information filtering for web service using machine learning has recently grown widely , since information overload has also becoming a serious problem on the World Wide Web. Recommender systems were designed to cater for this problem, but published recommender systems still fail to cope with changes of user's preferences. This paper summarizes a research that is still going on, to solve the lack of novelty, serendipity and dynamism in recommender systems. Recent research has demonstrated different methodologies to create recommender systems , unfortunately many of these which were evaluated using user-centric evaluation frameworks fall short to fulfill users' satisfaction. Therefore we propose a unique computational method to create a novel, serendipitous and dynamic recommender system. We used web content mining to gather user profiles from social media, model these profiles, and create an algorithm to suggest user preferences. The results testify that many users' social profiles for Zimbabweans dominate quite well to determine user preferences. Therefore recommender developers for developing countries, has to gather user's social profiles to predict their preferences. The main contribution is a holistic approach to model and predict dynamic user-specific preferences from categorized social media profiles namely: social, psychological, cultural, and economic profiles

show abstract

Improving the design of a recommendation system using evaluation criteria and metrics as a guide

Afolabi

Toivanen

2019

JSIT

View full text Add to dashboard Cite

Purpose The roles recommendation systems play in health care have become crucial in achieving effective care and in meeting the needs of modern care giving. As a result, efforts have been geared toward using recommendation systems in the management of chronic diseases. Effectiveness of these systems is determined by evaluation following implementation and before deployment, using certain metrics and criteria. The purpose of this study is to ascertain whether consideration of criteria during the design of a recommendation system can increase acceptance and usefulness of the recommendation system. Design/methodology/approach Using survey-style requirements gathering method, the specific health and technology needs of people living with chronic diseases were gathered. The result was analyzed using quantitative method. Sets of harmonized criteria and metrics were used along with requirements gathered from stakeholders to establish relationship among the criteria and the requirements. A matching matrix was used to isolate requirements for prioritization. These requirements were used in the design of a mobile app. Findings Matching criteria against requirements highlights three possible matches, namely, exact, inferential and zero matches. In any of these matches, no requirement was discarded. This allows priority features of the system to be isolated and accorded high priority during the design. This study highlights the possibility of increasing the acceptance rate and usefulness of a recommendation system by using metrics and criteria as a guide during the design process of recommendation systems in health care. This approach was applied in the design of a mobile app called Recommendations Sharing Community for Aged and Chronically Ill People. The result has shown that with this method, it is possible to increase acceptance rate, robustness and usefulness of the product. Research limitations/implications Inability to know the evaluation criteria beforehand, inability to do functional analysis of requirements, lack of well-defined requirements and often poor cooperation from people living with chronic diseases during requirements gathering for fear of stigmatization, confidentiality and privacy breaches are possible limitations to this study. Practical implications The result has shown that with this method, it is possible to isolate more important features of the system and use them during the design process, thereby speeding up the design and increasing acceptance rate, robustness and usefulness of the system. It also helps to see in advance the likely features of the system that will enhance its usefulness and acceptance, thereby increasing the confidence of the developers in their ability to deliver a system that will meet users’ needs. As a result, developers know beforehand where to concentrate their efforts during system development to ascertain the possibility of increasing usefulness and acceptance rate of a recommendation system. In addition, it will also save time and cost. Originality/value This paper demonstrates originality by highlighting and testing the possibility of using evaluation criteria and metrics during the design of a recommender system with a view to increasing acceptance and enhancing usefulness. It also shows the possibility of using the metrics and criteria in system’s development process for an exercise other than evaluation.

show abstract

A Characterisation and Framework for User-Centric Factors in Evaluation Methods for Recommender Systems

Cited by 5 publications

References 22 publications

Holistic User Context-Aware Recommender Algorithm

Holistic User Context-Aware Recommender Algorithm

A Novel, Serendipitous and Dynamic User-Centric Recommender Algorithm

Improving the design of a recommendation system using evaluation criteria and metrics as a guide

Contact Info

Product

Resources

About