Recommending Texts to Children with an Expert in the Loop

@inproceedings{Pera2018RecommendingTT,
  title={Recommending Texts to Children with an Expert in the Loop},
  author={Maria Soledad Pera and Katherine Landau Wright and Michael D. Ekstrand},
  year={2018}
}
In this position paper we discuss a number of open problems we believe the community should address in order to enhance the recommendation task for children. We specifically outline algorithmic and evaluation limitations when it comes to recommending reading materials for children in the classroom setting. Furthermore, we focus on the need to involve an expert (e.g., teacher) as part of the recommendation process to better serve the population under study. 
Retrieving and Recommending for the Classroom
TLDR
The promise and challenges of deploying recommendation and information retrieval technology to help teachers locate resources for use in classroom instruction are considered and work in progress is described including insights from interviews with working teachers.
Retrieving and Recommending for the Classroom: Stakeholders, Objectives, Resources, and Users
TLDR
The promise and challenges of deploying recommendation and information retrieval technology to help teachers locate resources for use in classroom instruction are considered and work in progress is described including insights from interviews with working teachers.
Educational Explainable Recommender Usage and its Effectiveness in High School Summer Vacation Assignment
Explainable recommendations, which provide explanations about why an item is recommended, help to improve the transparency, persuasiveness, and trustworthiness. However, few research in educational
BrainHood: towards an explainable recommendation system for self-regulated cognitive training in children
TLDR
A system for self-regulated cognitive training for children is proposed, which enables the child to reflect on their own progress, weaknesses and strengths, and self-arrange their training materials, promoting self- regulated learning skills.
BrainHood: Designing a cognitive training system that supports self-regulated learning skills in children
BACKGROUND: There is strong evidence that cognitive skills and executive functions are skills that children need in order to successfully learn in school. Although executive function disorders are
Evaluating Recommender Systems with and for Children: towards a Multi-Perspective Framework
TLDR
A multi-perspective framework for the evaluation of RSs for children is proposed, which integrates knowledge from disciplines such as engineering, cognitive science and humancomputer interaction.
BrainHood

References

SHOWING 1-9 OF 9 REFERENCES
Challenges in Evaluating Recommendations for Children
TLDR
Several of the challenges I see in evaluatingRecommender systems for children, how they relate to similar problems for general audiences, and why existing solutions from the recommender systems community are insufficient are described.
Automating readers' advisory to make book recommendations for K-12 readers
TLDR
The design of Rabbit is unique, since it adopts a multi-dimensional approach to capture the reading abilities, preferences, and interests of its readers, which goes beyond the traditional book content/topical analysis.
Reading Assessment: Linking Language, Literacy, and Cognition
TLDR
This book discusses reading theory and Stages of Reading Acquisition, as well as the role of Intellectual Assessment in the development of children's reading skills.
Context-aware recommender systems
TLDR
This chapter argues that relevant contextual information does matter in recommender systems and that it is important to take this information into account when providing recommendations, and introduces three different algorithmic paradigms for incorporating contextual information into the recommendation process.
Recommender Systems in Technology Enhanced Learning
Manouselis, N., Drachsler, H., Vuorikari, R., Hummel, H. G. K., & Koper, R. (2011). Recommender Systems in Technology Enhanced Learning. In P. B. Kantor, F. Ricci, L. Rokach, & B. Shapira (Eds.),
BPR: Bayesian Personalized Ranking from Implicit Feedback
TLDR
This paper presents a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem and provides a generic learning algorithm for optimizing models with respect to B PR-Opt.
Group Recommender Systems: An Introduction
Matrix Factorization Techniques for Recommender Systems
Looking for Information—A Survey of Research on Information Seeking, Needs, and Behavior