Measuring the User Satisfaction in a Recommendation Interface with Multiple Carousels

@article{Felicioni2021MeasuringTU,
  title={Measuring the User Satisfaction in a Recommendation Interface with Multiple Carousels},
  author={Nicol{\`o} Felicioni and Maurizio Ferrari Dacrema and Paolo Cremonesi},
  journal={ACM International Conference on Interactive Media Experiences},
  year={2021}
}
It is common for video-on-demand and music streaming services to adopt a user interface composed of several recommendation lists, i.e., widgets or swipeable carousels, each generated according to a specific criterion or algorithm (e.g., most recent, top popular, recommended for you, editors’ choice, etc.). Selecting the appropriate combination of carousel has significant impact on user satisfaction. A crucial aspect of this user interface is that to measure the relevance a new carousel for the… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 24 REFERENCES
Avoiding monotony: improving the diversity of recommendation lists
  • Mi Zhang, N. Hurley
  • Computer Science
    RecSys '08
  • 2008
TLDR
This work model the competing goals of maximizing the diversity of the retrieved list while maintaining adequate similarity to the user query as a binary optimization problem, leading to a parameterized eigenvalue problem whose solution is finally quantized to the required binary solution.
Updatable, Accurate, Diverse, and Scalable Recommendations for Interactive Applications
TLDR
A novel graph vertex ranking recommendation algorithm called RP3β that reranks items based on three-hop random walk transition probabilities is presented that provides accurate recommendations with high long-tail item frequency at the top of the recommendation list and is extended for online updates at interactive speeds.
Semantically Enhanced Collaborative Filtering on the Web
TLDR
This paper introduces an approach for semantically enhanced collaborative filtering in which structured semantic knowledge about items, extracted automatically from the Web based on domain-specific reference ontologies, is used in conjunction with user-item mappings to create a combined similarity measure and generate predictions.
Offline Evaluation to Make Decisions About PlaylistRecommendation Algorithms
TLDR
The results show that, contrary to much of the previous work on this topic, properly-conducted offline experiments do correlate well to A/B test results, and moreover that the authors can expect an offline evaluation to identify the best candidate systems for online testing with high probability.
Whole Page Optimization with Global Constraints
TLDR
This work derives a novel primal-dual algorithm which incorporates local diversity constraints as well as global business constraints for whole page optimization for Amazon video homepage, the first unified framework for dealing with relevance, diversity, and business constraints simultaneously.
Gaze Prediction for Recommender Systems
TLDR
This work shows that it is possible to predict gaze by combining easily-collected user browsing data with eye tracking data from a small number of users in a grid-based recommender interface, and demonstrates that Hidden Markov Models (HMMs) can be applied in this setting.
Using Navigation to Improve Recommendations in Real-Time
TLDR
This work proposes a novel strategy to address the problem of adapting the recommendations on a user's homepage by inferring the within-session user intent on-the-fly based on navigation interactions, and defines a new Bayesian model with an efficient inference algorithm.
Carousel Personalization in Music Streaming Apps with Contextual Bandits
TLDR
This paper model carousel personalization as a contextual multi-armed bandit problem with multiple plays, stochastic arm display and delayed batch feedback, and empirically shows the effectiveness of this framework at capturing characteristics of real-world carousels by addressing a large-scale playlist recommendation task on a global music streaming mobile app.
A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation
TLDR
It is found that results of offline and online evaluations often contradict each other, and it is concluded that offline evaluations may be inappropriate for evaluating research paper recommender systems, in many settings.
IR evaluation methods for retrieving highly relevant documents
TLDR
The novel evaluation methods and the case demonstrate that non-dichotomous relevance assessments are applicable in IR experiments, may reveal interesting phenomena, and allow harder testing of IR methods.
...
1
2
3
...