Surprise and Curiosity in A Recommender System

Al-Doulat, Ahmad

doi:10.1109/aiccsa.2018.8612897

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, studies have found that the knowledge of the media users' surprise and curiosity can help to build a curiosity-driven recommendation system. Importantly, this model achieves better performance compared to models that do not account for individual user personality characteristics (Al-Doulat, 2018;Shrestha et al, 2020). Similarly, evidence suggests that, when fit with information about emotional features of media content and media user emotional state, recommendation systems can produce more accurate and dynamic music recommendation effectiveness (Moscato et al, 2021).…”

Section: Using Predictive Models To Inform Explanatory Modelsmentioning

confidence: 89%

Media selection is highly predictable, In principle

gong¹,

Huskey²

2023

Preprint

View full text Add to dashboard Cite

Media researchers aim to accurately explain and predict people’s media selection. Explanation is an accurate description of the causal mechanisms that govern media selection whereas prediction is focused on making accurate inferences about unobserved data. However, meta-analyses demonstrate that existing media selection theories and models have limited explanatory accuracy. The predictive accuracy of these theories and models is unknown. Our project bridges this gap by empirically specifying how predictable, in principle, media selection is. To achieve this ambition, we articulate key conceptual distinctions between explanation and prediction. Subsequently, we report two empirical studies that estimate the theoretical maximum predictability of people’s music-listening and web-browsing behaviors. Approximately 80% of music selection and 60\% of web-browsing behaviors are predictable. Moreover, a simple Markov Chain model that uses information about people’s prior media selection can achieve about 20% prediction accuracy for music selection and 10% accuracy in predicting web-browsing. By estimating the maximum predictability of people’s media selection behavior, we gain a first-ever benchmark by which media selection theories and models can be compared. More broadly, we show how simple models that account for the sequential dependency in media selection lend new insights and suggest novel directions for future theory development.

show abstract

Section: Using Predictive Models To Inform Explanatory Modelsmentioning

confidence: 89%

Media selection is highly predictable, In principle

gong¹,

Huskey²

2023

Preprint

View full text Add to dashboard Cite

show abstract

A Survey of the State-of-the-Art and Some Extensions of Recommender System Based on Big Data

Jia

Feng

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

A Survey of Privacy Solutions using Blockchain for Recommender Systems: Current Status, Classification and Open Issues

Abduljabbar

Tao

Zhang

et al. 2021

The Computer Journal

View full text Add to dashboard Cite

Due to the rapid growth of Internet, E-commerce and Internet of Things, people use Web based services for most of their needs including buying items, reading books, watching online shows etc. Several companies are using recommender systems to influence people’s choices based on their likings, behaviours etc. Hence, people fear that their privacy is violated. Also, some of the online applications are not safe and secure. One way to overcome the privacy related issues is using secured solutions such as incorporating blockchain technologies for privacy-based applications. The decentralized nature of blockchain technologies have resolved several security, and authentication problems of Internet of Things systems. In this paper, we conduct a comprehensive survey on the privacy solutions for recommender systems emphasising current status, classification and open issues. We also discuss blockchain technology, including its structure as well as applications of blockchain technology for privacy solutions of recommender systems. Furthermore, we discuss the limitations and delve into future trends that blockchain technology can be adapted for privacy-base applications in the years to come.

show abstract

Surprise and Curiosity in A Recommender System

Cited by 3 publications

References 4 publications

Media selection is highly predictable, In principle

Media selection is highly predictable, In principle

A Survey of the State-of-the-Art and Some Extensions of Recommender System Based on Big Data

A Survey of Privacy Solutions using Blockchain for Recommender Systems: Current Status, Classification and Open Issues

Contact Info

Product

Resources

About