English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The first part of this thesis focuses on maximizing the overallrecommendation accuracy. This accuracy is usually evaluated with someuser-oriented metric tailored to the recommendation scenario, but becauserecommendation is usually treated as a machine learning problem, recommendationmodels are trained to maximize some other generic criteria that does notnecessarily align with the criteria ultimately captured by the user-orientedevaluation metric. Recent research aims at bridging this gap between trainingand evaluation via direct ranking optimization, but still assumes that themetric used for evaluation should also be the metric used for training. Wechallenge this assumption, mainly because some metrics are more informativethan others. Indeed, we show that models trained via the optimization of a lossinspired by Rank-Biased Precision (RBP) tend to yield higher accuracy, evenwhen accuracy is measured with metrics other than RBP. However, the superiorityof this RBP-inspired loss stems from further benefiting users who are alreadywell-served, rather than helping those who are not.  This observation inspires the second part of this thesis, where our focusturns to helping non-mainstream users. These are users who are difficult torecommend to either because there is not enough data to model them, or becausethey have niche taste and thus few similar users to look at when recommendingin a collaborative way. These differences in mainstreamness introduce a biasreflected in an accuracy gap between users or user groups, which we try tonarrow.

Metric Optimization and Mainstream Bias Mitigation in Recommender Systems