A Switching Approach that Improves Prediction Accuracy for Long Tail Recommendations

Alshammari, Gharbi; Jorro-Aragoneses, Jose L.; Kapetanakis, Stelios; Polatidis, Nikolaos; Petridis, Miltos

doi:10.1007/978-3-030-29516-5_3

Cited by 4 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, this activity is largely focussed on a very small set of highly popular items, leaving a long tail of items that remain unnoticed and, because of that, remain unpopular. These factors contribute to the issue that a potentially very large set of candidate items is reduced to a relatively small pool of candidate items to be recommended (Celma, 2010;Polatidis & Petridis, 2019).…”

Section: Filter Bubbles Echo Chambers Bias and Routinementioning

confidence: 99%

Breaking the routine: spatial hypertext concepts for active decision making in recommender systems

Atzenbeck¹,

Herder

Roßner³

2023

New Review of Hypermedia and Multimedia

View full text Add to dashboard Cite

Recommender Systems are omnipresent in our digital life. Most notably, various media platforms guide us in selecting videos, but recommender systems are also used for more serious goals, such as news selection, political orientation and work decisions. As argued in this survey and position article, the paradigm of recommendation-based feeds has changed user behaviour from active decision making to rather passively following recommendations and accepting possibly suboptimal choices that are deemed "good enough". We provide a historic overview of media selection, discuss assumptions and goals of recommender systems and identify their shortcomings, based on existing literature. Then, the perspective changes to hypertext as a paradigm for structuring information and active decision making. To illustrate the relevance and importance of active decision making, we present a use case in the field of TV or media selection and (as a proof of concept) carried over to another application domain: maintenance in industry. In the discussion section, we focus on categorising these actions on a spectrum of "system-1" (fast and automated) tasks and "system-2" (critical thinking) tasks. Further, we argue how users can profit from tools that combine active (spatial) structuring and categorising with automatic recommendations, for professional tasks as well as private, leisure activities.

show abstract

Section: Filter Bubbles Echo Chambers Bias and Routinementioning

confidence: 99%

Breaking the routine: spatial hypertext concepts for active decision making in recommender systems

Atzenbeck¹,

Herder

Roßner³

2023

New Review of Hypermedia and Multimedia

View full text Add to dashboard Cite

show abstract

“…Each user has rated at least 20 movies. It contains 100,000 ratings, all of which are in a range between 1…”

Section: Movielens 100kmentioning

confidence: 99%

“…Recommender systems (RS) are decision support systems well known for their use in filtering and finding the relevant products on the web, thus solving the informtion overload problem. RS can make a huge impact on both sides: (1) increasing the sales of a business and (2) reduce the burden of users by finding and recommending interesting items. These recommendations rely on user interaction and behaviour tracking and analysis using artificial intelligence approaches [1].…”

Section: Introductionmentioning

confidence: 99%