Recommender systems: from algorithms to user experience

By J. Konstan, John Riedl. User modeling and user-adapted interaction, 2012

857 citations recorded by the source corpus.

Subfields: Computer Science Applications, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/058e1c94d68da04fa839022c1b48c8caf15c93ab

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Science Applications

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Recommendation systems: Principles, methods and evaluation (2015, background): “Recommender systems are information ﬁltering systems that deal with the problem of information overload [1] by ﬁlter-ing vital information fragment out of large amount of dynamically generated information according to user’s preferences, interest,orobservedbehavioraboutitem[2].”
Evaluating Recommender Systems with User Experiments (2015, background): “We reiterate the conclusion by [72, 111] that future work should explore how explanations can help to reduce choice overload and otherwise improve users’ decision-making.”
Recommender Systems: Introduction and Challenges (2015, background): “papers for additional material [13, 30, 34, 40, 44].”
Explanations as Mechanisms for Supporting Algorithmic Transparency (2018, background): “Algorithms that make autonomous decisions and provide recommendations are a “mission critical” aspect of many online content and e-commerce platforms, including Facebook, Google, Netflix, and Amazon [28, 29, 39].”
Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols (2013, background): “Online evaluation can be considered preferable to offline evaluation, mainly due to its ability to take into account the user’s experience (Knijnenburg et al. 2012; Konstan and Riedl 2012).”
A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation (2013, background): “For a comprehensive overview of offline evaluations including evaluation metrics and potential problems refer to [4,18,19].”
Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy (2020, neutral): “The goals of RST are most relevant for life-critical systems, but there are many consumer and professional applications: Recommender systems: these are widely used in advertising services, social media platforms, and search engines have brought strong benefits to consumers (Konstan & Riedl, 2012).”
Interactive Visual Profiling of Musicians (2016, background): “In the last two decades, many different recommendation algorithms have been developed [39].”
Research-paper recommender systems: a literature survey (2015, background): “For a comprehensive overview of offline evaluations, refer to [274,275].”
Are we really making much progress? A worrying analysis of recent neural recommendation approaches (2019, background): “The hunt for better accuracy values dominates research activities in this area, even though it is not even clear if slightly higher accuracy values are relevant in terms of adding value for recommendation consumers or providers [20, 22, 52].”
Recommendation Systems in Software Engineering (2014, methodology): “[19] proposed a modification to the standard K-means algorithm.”
Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities (2016, background): “These factors affect user satisfaction (Tintarev and Masthoff, 2011; Pu et al., 2012; Konstan and Riedl, 2012) and can play an important role in improving current recommender systems.”
Explaining the user experience of recommender systems (2012, methodology): “Researchers in the field of algorithm accuracy predominantly use behavioral data for their evaluations: they use logged clicks (either item selections or ratings) to train and test their algorithms (Konstan and Riedl 2012).”
User Preferences for Hybrid Explanations (2017, background): “E ective recommendations must be both accurate and explainable [9, 10, 13, 16].”