Toward personalized XAI: A case study in intelligent tutoring systems

Conati, Cristina; Barral, Oswald; Putnam, Vanessa; Rieger, Lea

doi:10.1016/j.artint.2021.103503

Cited by 90 publications

(58 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Section A includes the respondent's demographic information, including gender, age, and work experience in related fields. Section B assesses the system's performance in system components, workflows, and development with game elements guidelines based on modifications from the previous study [11,56,57]. A total of 15 items were constructed; each was rated according to the 5-point Likert scale, from 1 -Very Not Important to 5 -Very Important.…”

Section: Instrumentmentioning

confidence: 99%

Conceptual Framework for an Adaptive Tutorial System with Gamification to Enhance Digital Literacy

Kaeophanuek

Chaisriya

2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

Digital literacy skills are essential skills for working in a digital society. Therefore, the university emphasizes teaching and finding ways to assess knowledge and prepare students before completing their studies. This research aims to present the conceptual framework for developing an adaptive tutorial system to assist undergraduate students in preparing for the digital literacy exit exam. This system's unique feature is not only the exam for students to practice reviewing their knowledge but also the exam's adaptability to the student's abilities. In addition, this concept is reinforced through gamification by incorporating game elements to motivate, increase the difficulty of competition and make exam preparation enjoyable. Learners are motivated to try harder on the exam. In the conceptual framework evaluation, a questionnaire was used to measure the system's suitability. The system design was evaluated by seven experts who determined that the components and procedures of the tutorial system were appropriate. This system's development is valid and can be applied to creating a tutorial system that enhances digital literacy skills.

show abstract

Section: Instrumentmentioning

confidence: 99%

Conceptual Framework for an Adaptive Tutorial System with Gamification to Enhance Digital Literacy

Kaeophanuek

Chaisriya

2022

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

show abstract

“…The approaches developed so far can be classified in (i) those that explain the system’s behavior (Conati et al. 2021 ; Kouki et al. 2020 ), (ii) those that fuse recommendation and explanation in the same process (Dong and Smyth 2017 ; Lu et al.…”

Section: Related Workmentioning

confidence: 99%

Justification of recommender systems results: a service-based approach

Mauro

Ardissono

2022

User Model User-Adap Inter

View full text Add to dashboard Cite

With the increasing demand for predictable and accountable Artificial Intelligence, the ability to explain or justify recommender systems results by specifying how items are suggested, or why they are relevant, has become a primary goal. However, current models do not explicitly represent the services and actors that the user might encounter during the overall interaction with an item, from its selection to its usage. Thus, they cannot assess their impact on the user’s experience. To address this issue, we propose a novel justification approach that uses service models to (i) extract experience data from reviews concerning all the stages of interaction with items, at different granularity levels, and (ii) organize the justification of recommendations around those stages. In a user study, we compared our approach with baselines reflecting the state of the art in the justification of recommender systems results. The participants evaluated the Perceived User Awareness Support provided by our service-based justification models higher than the one offered by the baselines. Moreover, our models received higher Interface Adequacy and Satisfaction evaluations by users having different levels of Curiosity or low Need for Cognition (NfC). Differently, high NfC participants preferred a direct inspection of item reviews. These findings encourage the adoption of service models to justify recommender systems results but suggest the investigation of personalization strategies to suit diverse interaction needs.

show abstract

“…Since then, work has been done to improve the understanding of personalized recommendations (Nunes and Jannach, 2017;Masthoff, 2012, 2022;Jannach et al, 2019). The approaches developed so far can be classified in (i) those that explain the system's behavior (Conati et al, 2021;Kouki et al, 2020), (ii) those that fuse recommendation and explanation in the same process (Dong and Smyth, 2017;Lu et al, 2018;Rana et al, 2022), and (iii) those that provide post-hoc justifications of the suggestions (Musto et al, 2021;Ni et al, 2019). While the last approach is agnostic to the recommendation algorithm, the first two are tightly coupled to it.…”

Section: Premisesmentioning

confidence: 99%

Justification of Recommender Systems Results: A Service-based Approach

Mauro,

Hu,

Ardissono

2022

Preprint

View full text Add to dashboard Cite

With the increasing demand for predictable and accountable Artificial Intelligence, the ability to explain or justify recommender systems results by specifying how items are suggested, or why they are relevant, has become a primary goal. However, current models do not explicitly represent the services and actors that the user might encounter during the overall interaction with an item, from its selection to its usage. Thus, they cannot assess their impact on the user's experience. To address this issue, we propose a novel justification approach that uses service models to (i) extract experience data from reviews concerning all the stages of interaction with items, at different granularity levels, and (ii) organize the justification of recommendations around those stages. In a user study, we compared our approach with baselines reflecting the state of the art in the justification of recommender systems results. The participants evaluated the Perceived User Awareness Support provided by our servicebased justification models higher than the one offered by the baselines. Moreover, our models received higher Interface Adequacy and Satisfaction evaluations by users having different levels of Curiosity or low Need for Cognition (NfC). Differently, high NfC participants preferred a direct inspection of item reviews. These findings encourage the adoption of service models to justify recommender systems results but suggest the investigation of personalization strategies to suit diverse interaction needs.

show abstract

Toward personalized XAI: A case study in intelligent tutoring systems

Cited by 90 publications

References 54 publications

Conceptual Framework for an Adaptive Tutorial System with Gamification to Enhance Digital Literacy

Conceptual Framework for an Adaptive Tutorial System with Gamification to Enhance Digital Literacy

Justification of recommender systems results: a service-based approach

Justification of Recommender Systems Results: A Service-based Approach

Contact Info

Product

Resources

About