Behaviorism is Not Enough: Better Recommendations through Listening to Users

  title={Behaviorism is Not Enough: Better Recommendations through Listening to Users},
  author={Michael D. Ekstrand and Martijn C. Willemsen},
  journal={Proceedings of the 10th ACM Conference on Recommender Systems},
Behaviorism is the currently-dominant paradigm for building and evaluating recommender systems. Both the operation and the evaluation of recommender system applications are most often driven by analyzing the behavior of users. In this paper, we argue that listening to what users say about the items and recommendations they like, the control they wish to exert on the output, and the ways in which they perceive the system and not just observing what they do will enable important developments in… 

Recommender system for developing new preferences and goals

The research will take a multidisciplinary approach in which insights from psychology on decision making and habit formation are paired with new approaches to recommendation that included preference evolution, interactive exploration methods and goal-directed approaches to evaluate the success of such algorithms.

Understanding User Preferences and Goals in Recommender Systems

It is shown how a user-centric approach can help better understand why users are satisfied or not, for example why users prefer diversify over prediction accuracy as it reduces choice difficulty.

Psychology-informed Recommender Systems

The aim of this survey is to present a thorough review of the state of the art of recommender systems that leverage psychological constructs and theories to model and predict user behavior and improve the recommendation process.

Towards psychology-aware preference construction in recommender systems: Overview and research issues

An overview of preference representations used in different types of recommender systems is provided and various factors such as personality traits, emotional states, and cognitive biases are influenced.

Designing for the better by taking users into account: a qualitative evaluation of user control mechanisms in (news) recommender systems

This paper focuses and elaborate on the concept of user control because that mitigates multiple problems at once and contributes to a richer understanding of why and how to design for user control in recommender systems.

How can they know that? A study of factors affecting the creepiness of recommendations

The creepiness of recommendations is investigated using an online experiment in three domains: movies, hotels, and health to find out that the perception of creepiness varies across domains and depends on recommendation features, like causal ambiguity and accuracy.

Personalized Recommendations for Music Genre Exploration

This is one of the first studies using a recommender system to support users' preference development, and provides insights in how recommender systems can help users attain new goals and tastes.

Practitioners Versus Users: A Value-Sensitive Evaluation of Current Industrial Recommender System Design

Value Sensitive Design is adopted to comprehensively explore how practitioners and users recognize different values of current industrial recommender systems, focusing on five values: recommendation quality, privacy, transparency, fairness, and trustworthiness.

Promoting Energy-Efficient Behavior by Depicting Social Norms in a Recommender Interface

It is shown that depicting high peer adoption rates alongside energy-saving measures increased the likelihood that they would be chosen from a list of recommendations, and that depicting social norms positively affects a user’s evaluation of a recommender interface.

How Intention Informed Recommendations Modulate Choices: A Field Study of Spoken Word Content

It is suggested that intention-aware recommendations can significantly raise users' interactions with channels and episodes related to intended topics by over 24%, even if such a recommender is only used during onboarding, and the CF-based recommender doubles users' explorations on episodes from not-subscribed channels and improves satisfaction for users onboarded with the intention- Aware recommender.



Putting Users in Control of their Recommendations

This work builds and evaluates a system that incorporates user-tuned popularity and recency modifiers, allowing users to express concepts like "show more popular items" and finds that users who are given these controls evaluate the resulting recommendations much more positively.

Letting Users Choose Recommender Algorithms: An Experimental Study

This study gives users the ability to change the algorithm providing their movie recommendations and studied how they make use of this power, and examines log data from user interactions with this new feature to under-stand whether and how users switch among recommender algorithms, and select a final algorithm to use.

User perception of differences in recommender algorithms

It is found that satisfaction is negatively dependent on novelty and positively dependent on diversity in this setting, and that satisfaction predicts the user's final selection of a recommender that they would like to use in the future.

Don't look stupid: avoiding pitfalls when recommending research papers

This work performs a detailed user study with over 130 users to understand differences between recommender algorithms through an online survey of paper recommendations from the ACM Digital Library, and succinctly summarizes the most striking results as "Don't Look Stupid" in front of users.

Making recommendations better: an analytic model for human-recommender interaction

It is argued that recommenders need a deeper understanding of users and their information seeking tasks and recommender algorithms using a common language and an analytic process model.

"I like to explore sometimes": Adapting to Dynamic User Novelty Preferences

It is shown that there are large individual and temporal differences in the users' novelty preferences and a regression model is developed to predict these dynamic novelty preferences of users using features derived from their past interactions.

Contextual Recommendation

This paper proposes a fundamental shift in terms of how a user is modeled within a recommendation system, inspired by models of human memory developed in psychology, and defines a recommendation process that uses these two memories.

Recommending and evaluating choices in a virtual community of use

A general history-of-use method that automates a social method for informing choice and report on how it fares in the context of a fielded test case: the selection of videos from a large set of videos.

Terms of a Feather: Content-Based News Recommendation and Discovery Using Twitter

A social news service called Buzzer is described that is capable of adapting to the conversations that are taking place on Twitter to ranking personal RSS subscriptions, and results of a live-user evaluation demonstrate how these ranking strategies can add better item filtering and discovery value to conventional recency-based RSS ranking techniques.

The Filter Bubble: How the New Personalized Web Is Changing What We Read and How We Think

In December 2009, Google began customizing its search results for all users, and we entered a new era of personalization. With little notice or fanfare, our online experience is changing, as the