Competitive gamification in crowdsourcing-based contextual-aware recommender systems

Lin, Yiling; Ding, Nai-Da

doi:10.1016/j.ijhcs.2023.103083

Cited by 3 publications

(3 citation statements)

References 109 publications

(156 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It assumes that there is an association between each user and the item. The recommendations are categorized into the following two types: userbased recommendation [11] and item-based recommendation [12]. User-based recommendation recommends items to users with similar preferences.…”

Section: Collaborative Filtering Recommendationmentioning

confidence: 99%

“…2 is the regularization parameter, 𝑼𝑼 𝑖𝑖 and 𝑽𝑽 𝑖𝑖 represent the latent feature vectors of students and questions in D dimensions, respectively, and ‖•‖ 𝐹𝐹𝐹𝐹𝑜𝑜 2 denotes the matrix normalization. Take the derivatives with respect to 𝑼𝑼 𝑖𝑖 , 𝑽𝑽 𝑖𝑖 : (12) Then update using the stochastic gradient descent method until convergence or reaching the maximum number of iterations. , .…”

Section: Affection-enhanced Personalized Question Recommendationmentioning

confidence: 99%

See 1 more Smart Citation

Affection-enhanced Personalized Question Recommendation in Online Learning

2023

KSII TIIS

View full text Add to dashboard Cite

With the popularity of online learning, intelligent tutoring systems are starting to become mainstream for assisting online question practice. Surrounded by abundant learning resources, some students struggle to select the proper questions. Personalized question recommendation is crucial for supporting students in choosing the proper questions to improve their learning performance. However, traditional question recommendation methods (i.e., collaborative filtering (CF) and cognitive diagnosis model (CDM)) cannot meet students' needs well. The CDM-based question recommendation ignores students' requirements and similarities, resulting in inaccuracies in the recommendation. Even CF examines student similarities, it disregards their knowledge proficiency and struggles when generating questions of appropriate difficulty. To solve these issues, we first design an enhanced cognitive diagnosis process that integrates students' affection into traditional CDM by employing the non-compensatory bidimensional item response model (NCB-IRM) to enhance the representation of individual personality. Subsequently, we propose an affection-enhanced personalized question recommendation (AE-PQR) method for online learning. It introduces NCB-IRM to CF, considering both individual and common characteristics of students' responses to maintain rationality and accuracy for personalized question recommendation. Experimental results show that our proposed method improves the accuracy of diagnosed student cognition and the appropriateness of recommended questions.

show abstract

Section: Collaborative Filtering Recommendationmentioning

confidence: 99%

Section: Affection-enhanced Personalized Question Recommendationmentioning

confidence: 99%

Affection-enhanced Personalized Question Recommendation in Online Learning

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…This not only helps mitigate the risk of not fully reaping the benefits of the initiative but also prevents the emergence of harmful behaviors resulting from the adopted solutions [7]. Crowdsourcing, coupled with a competitive game design, motivates platform users not only to strive for improved performance but also to undertake a more extensive array of tasks [8]. For this reason, an increasing number of crowdsourcing platforms are incorporating game-inspired techniques to boost user participation and enhance the quality of the produced work [9].…”

Section: Introductionmentioning

confidence: 99%

Gamifying Cultural Heritage: The Digitization Journey of Genoa University Museum System (SMA-UniGe)

La Tessa,

Schiaparelli,

Coccoli

et al. 2024

Preprint

View full text Add to dashboard Cite

The extensive collection of paper documents and books stored in the archives of universities worldwide is a hidden cultural heritage that is frequently inaccessible. To overcome this problem, the University of Genoa, Italy, seeks to collect, store, and digitize a wide variety of items, encompassing books, manuscripts, archival materials, and documents related to museum artifacts, which together form a cultural heritage of great importance and historical significance. To make such a cultural heritage accessible to both humans and machines, images and videos must be provided with alternate descriptions, metadata, and speech-to-text transcriptions while ancient texts, for which OCR techniques are often not effective, must be accompanied by word-for-word transcripts. This work presents the design of a transcription system for the “University Museum System” at the University of Genoa, Italy (SMA-UniGe), including user interface elements and users’ engagement techniques. The goal is to create an accessible digital heritage that can be enjoyed by all, facilitated by a community of digital volunteers who are eager to dedicate their time, have a great experience, socialize, and interact on the proposed transcription system. The system exploits gamification theory to transform the typically monotonous task of transcription into a captivating experience. This activity is in line with the so-called University third mission, i.e., the activity of public engagement that aims at generating knowledge outside the academic environment to the benefit of the social, cultural, and economic development.

show abstract

Gamification as a panacea to workplace cyberloafing: an application of self-determination and social bonding theories

Nivedhitha,

Giri,

Pasricha

2024

INTR

View full text Add to dashboard Cite

PurposeGamification has been constantly demonstrated as an effective mechanism for employee engagement. However, little is known about how gamification reduces cyberloafing and the mechanism by which it affects cyberloafing in the workplace. This study draws inspiration from self-determination and social bonding theories to explain how game dynamics, namely, personalised challenges, social interactivity and progression status, enhance tacit knowledge sharing behaviour, which, in turn, reduces cyberloafing. In addition, the study also examines the negative moderating effect of fear of failure on the positive relationship between game dynamics and tacit knowledge sharing.Design/methodology/approachUsing a sample of 250 employees from information technology organisations, the study employed a 3-wave study to examine the conditional indirect effects.FindingsThe results ascertain that tacit knowledge sharing plays a central role in the relationship between gamification and cyberloafing. Further, game dynamics positively influenced tacit knowledge sharing, which in turn reduced cyberloafing. Especially, social interactivity and progression status greatly reduced cyberloafing behaviour when the fear of failure was low.Originality/valueThis study is one of the initial studies that suggest gamification as a progressive tool to reduce workplace cyberloafing behaviours. It utilises a problematisation approach to analyse and criticise the in-house assumptions regarding cyberloafing prevention measures. Further, the study proposes a conceptual model explaining the link between gamification and cyberloafing through alternate assumptions.

show abstract

Competitive gamification in crowdsourcing-based contextual-aware recommender systems

Cited by 3 publications

References 109 publications

Affection-enhanced Personalized Question Recommendation in Online Learning

Affection-enhanced Personalized Question Recommendation in Online Learning

Gamifying Cultural Heritage: The Digitization Journey of Genoa University Museum System (SMA-UniGe)

Gamification as a panacea to workplace cyberloafing: an application of self-determination and social bonding theories

Contact Info

Product

Resources

About