Exploring Mental Models for Transparent and Controllable Recommender Systems: A Qualitative Study

Ngo, Thao; Kunkel, Johannes; Ziegler, Jürgen

doi:10.1145/3340631.3394841

Cited by 54 publications

(55 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the others, individuals might have had less cognitive representations about the functioning, thus leading to more humanization than our study. In fact, for intelligent systems, prior research could show that users can hold distinct concept-based and processed-based components in their user understanding (Kunkel et al, in press;Ngo et al, 2020). These distinct and more mechanistic components might have decreased the likelihood of humanization.…”

Section: Effects Of Humanization On Perceived and Objective User Unde...mentioning

confidence: 99%

“…The second mechanism concerns a phenomenon that can occur when individuals face technology: Humanization (also called anthropomorphism) is the process of attributing human characteristics and states to non-human agents by using one's very own as an anchor (Epley et al, 2007). Humanization can be an inherent part of user understanding (Kodama et al, 2017;Ngo et al, 2020;Wu et al, 2019). Individuals tend to humanize, especially when systems appear unpredictable and they feel uncertain about their behavior (Epley et al, 2007;Waytz et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

I humanize, therefore I understand? Effects of explanations and humanization of intelligent systems on perceived and objective user understanding

Ngo¹,

Krämer²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The functioning of intelligent systems can be opaque to users. Yet, users need to make informed choices about them. This work compares two knowledge mechanisms, i.e., ways for users to achieve an understanding of intelligent systems: explanation and humanization. In online experiment (N = 416), we compared the effects of a control condition without any explanation against a) aneutral and b) a humanized how-explanations as well as c) active humanization on (perceived and objective) user understanding and systems perceptions (trust, transparency, satisfaction, perceived usefulness). Our main finding: Explanations increased transparency and perceived understanding but not objective understanding. Active humanization, surprisingly, decreased objective understanding compared to the control condition suggesting inhibition of knowledge retrieval. Humanized how-explanation increased the perceived usefulness. We found no effects for trust and satisfaction. We conclude that explanations lead to a deceptive feeling of understanding. Explanations shouldconsider the prior understanding to affect objective understanding.

show abstract

Section: Effects Of Humanization On Perceived and Objective User Unde...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

I humanize, therefore I understand? Effects of explanations and humanization of intelligent systems on perceived and objective user understanding

Ngo¹,

Krämer²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prior research on user perception of the recommender system has shown that users possess a cognitive model of how the system works [3,2]. Cognitive models or mental models can be described as the internal representations that users build based on their interactions with the target system [4,5].…”

Section: Related Workmentioning

confidence: 99%

“…Prior research demonstrates that users possess a cognitive model of how recommender systems work [1,2,3]. This cognitive model represents the users' interpretation of how the system operates, what their objectives are, and how they generate recommendations.…”

Section: Introductionmentioning

confidence: 99%

How does the User's Knowledge of the Recommender Influence their Behavior?

Ghori,

Dehpanah,

Gemmell

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender systems have become a ubiquitous part of modern web applications. They help users discover new and relevant items. Today's users, through years of interaction with these systems have developed an inherent understanding of how recommender systems function, what their objectives are, and how the user might manipulate them. We describe this understanding as the Theory of the Recommender. In this study, we conducted semi-structured interviews with forty recommender system users to empirically explore the relevant factors influencing user behavior. Our findings, based on a rigorous thematic analysis of the collected data, suggest that users possess an intuitive and sophisticated understanding of the recommender system's behavior. We also found that users, based upon their understanding, attitude, and intentions change their interactions to evoke desired recommender behavior. Finally, we discuss the potential implications of such user behavior on recommendation performance.

show abstract

“…[14,17]. Data driven CDSSs and recommender systems are uncommon in clinical practice, mostly due the perception that they are a 'black box' tool [6] with a decision process that lacks transparency, even though transparent recommender systems exist [18,19].…”

Section: Introductionmentioning

confidence: 99%

A Treatment Recommender Clinical Decision Support System for Personalized Medicine: Method Development and Proof-of-concept for Drug Resistant Tuberculosis

Verboven

Calders

Callens

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundIndividualised or precision medicine tailors care based on the patient’s or pathogen’s genotypic and phenotypic characteristics. An automated Clinical Decision Support System (CDSS) could help translate the genotypic and phenotypic characteristics into optimal treatment and thus facilitate implementation of individualized treatment by less experienced physicians.MethodsWe developed a hybrid knowledge- and data-driven treatment recommender CDSS. Stakeholders and experts first define the knowledge base by identifying and quantifying drug and regimen features for the prototype model input. In an iterative manner, feedback from experts is harvested to generate model training datasets, machine learning methods are applied to identify complex relations and patterns in the data, and model performance is assessed by estimating the precision at one, mean reciprocal rank and mean average precision. Once the model performance no longer iteratively increases, a validation dataset is used to assess model overfitting. ResultsWe applied the novel methodology to develop a treatment recommender CDSS for individualized treatment of drug resistant tuberculosis as a proof of concept. Using input from stakeholders and three rounds of expert feedback on a dataset of 355 patients with 129 unique drug resistance profiles, the model had a 95% precision at 1 indicating that the highest ranked treatment regimen was considered appropriate by the experts in 95% of cases. Use of a validation data set however suggested substantial model overfitting, with a reduction in precision at 1 to 78%. ConclusionOur novel and flexible hybrid knowledge- and data-driven treatment recommender CDSS is a first step towards the automation of individualized treatment for personalized medicine. Further research should assess its value in fields other than drug resistant tuberculosis, develop solid statistical approaches to assess model performance, and evaluate their accuracy in real-life clinical settings.

show abstract

Exploring Mental Models for Transparent and Controllable Recommender Systems: A Qualitative Study

Cited by 54 publications

References 29 publications

I humanize, therefore I understand? Effects of explanations and humanization of intelligent systems on perceived and objective user understanding

I humanize, therefore I understand? Effects of explanations and humanization of intelligent systems on perceived and objective user understanding

How does the User's Knowledge of the Recommender Influence their Behavior?

A Treatment Recommender Clinical Decision Support System for Personalized Medicine: Method Development and Proof-of-concept for Drug Resistant Tuberculosis

Contact Info

Product

Resources

About