HCI.TOPHCI, made easy

arrow_backBack to questions View categoryarrow_forward

AI Explainability, Trust, and Calibration / Explanation, Control, and Trust in Recommendation Systems

Users struggle to understand recommendation results through static review explanations due to insufficient interactivity.

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users struggle to understand recommendation results through static review explanations due to insufficient interactivity.

CUI '21Conversational Review-Based Explanations for Recommender Systems: Exploring Users’ Query Behavior

Similar questions

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users lack trust in recommendation system content and do not understand recommendation rationales.

IUI '24Leveraging ChatGPT for Automated Human-centered Explanations in Recommender Systems

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Adolescents struggle to understand and trust algorithmically recommended learning content.

IUI '23Steering Recommendations and Visualising Its Impact: Effects on Adolescents’ Trust in E-Learning Platforms

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users have a trust crisis toward health recommendation systems based on social media data.

CHI '23When Recommender Systems Snoop into Social Media, Users Trust them Less for Health Advice

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users do not trust recommendation results because the embedding models used by recommender systems are too difficult to explain.

IUI '22Similarity-Based Explanations meet Matrix Factorization via Structure-Preserving Embeddings

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users face heavy burden managing recommended file operations one by one in cloud storage.

UIST '22Summarizing Sets of Related ML-Driven Recommendations for Improving File Management in Cloud Storage

lightbulbPractical problemExplanation, Control, and Trust in Recommendation Systems

Users have insufficient trust in recommendation systems, especially during cold-start phases.

CHI '22User Trust in Recommendation Systems: A comparison of Content-Based, Collaborative and Demographic Filtering

Related papers

Leveraging ChatGPT for Automated Human-centered Explanations in Recommender Systems

Ítallo Silva, Leandro Marinho, Alan Said

When Recommender Systems Snoop into Social Media, Users Trust them Less for Health Advice

Yuan Sun, Magdalayna Drivas, Mengqi Liao

Similarity-Based Explanations meet Matrix Factorization via Structure-Preserving Embeddings

Leandro Balby Marinho, Júlio Guedes, Denis Parra

Summarizing Sets of Related ML-Driven Recommendations for Improving File Management in Cloud Storage

Will Brackenbury, Kyle Chard, Aaron Elmore

User Trust in Recommendation Systems: A comparison of Content-Based, Collaborative and Demographic Filtering

Mengqi Liao, S. Shyam Sundar, Joseph B. Walther

Impacts of Personal Characteristics on User Trust in Conversational Recommender Systems

Wanling Cai, Yucheng Jin, Li Chen

From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks

Hyeonsu B Kang, Rafal Kocielnik, Andrew Head

Vis Ex Machina: An Analysis of Trust in Human versus Algorithmically Generated Visualization Recommendations

Rachael Zehrung, Astha Singhal, Michael Correll

The Effects of Warmth and Competence Perceptions on Users' Choice of an AI System

Zohar Gilad, Ofra Amir, Liat Levontin