Projekteja vuodessa
Abstrakti
Recommender systems typically suggest to users content similar to what they consumed in the past. If a user happens to be exposed to strongly polarized content, she might subsequently receive recommendations which may steer her towards more and more radicalized content, eventually being trapped in what we call a "radicalization pathway". In this paper, we study the problem of mitigating radicalization pathways using a graphbased approach. Specifically, we model the set of recommendations of a "whattowatchnext" recommender as a dregular directed graph where nodes correspond to content items, links to recommendations, and paths to possible user sessions. We measure the "segregation" score of a node representing radicalized content as the expected length of a random walk from that node to any node representing nonradicalized content. High segregation scores are associated to larger chances to get users trapped in radicalization pathways. Hence, we define the problem of reducing the prevalence of radicalization pathways by selecting a small number of edges to "rewire", so to minimize the maximum of segregation scores among all radicalized nodes, while maintaining the relevance of the recommendations. We prove that the problem of finding the optimal set of recommendations to rewire is NPhard and NPhard to approximate within any factor. Therefore, we turn our attention to heuristics, and propose an efficient yet effective greedy algorithm based on the absorbing random walk theory. Our experiments on realworld datasets in the context of video and news recommendations confirm the effectiveness of our proposal.
Alkuperäiskieli  englanti 

Otsikko  WWW'22: Proceedings of the ACM Web Conference 2022 
Sivumäärä  10 
Kustantaja  Association for Computing Machinery 
Julkaisupäivä  huhtik. 2022 
Sivut  2719–2728 
ISBN (elektroninen)  9781450390965 
DOI  pysyväislinkit  
Tila  Julkaistu  huhtik. 2022 
OKMjulkaisutyyppi  A4 Artikkeli konferenssijulkaisuussa 
Tapahtuma  The ACM Web Conference  Lyon, Ranska Kesto: 25 huhtik. 2022 → 29 huhtik. 2022 
Tieteenalat
 113 Tietojenkäsittely ja informaatiotieteet
Projektit
 1 Aktiivinen

MLDB: Model Management Systems: Machine learning meets Database Systems
Gionis, A., Mathioudakis, M., Merchant, A., Pai, S. G., Svana, M. & Wang, Y.
Suomen Akatemia Projektilaskutus
01/09/2019 → 31/12/2023
Projekti: Suomen Akatemia: Akatemiahanke
Palkinnot

Best paper award at the ACM Web Conference 2022
Fabbri, Francesco (Vastaanottaja), Wang, Yanhao (Vastaanottaja), Bonchi, Francesco (Vastaanottaja), Castillo, Carlos (Vastaanottaja) & Mathioudakis, Michael (Vastaanottaja), 29 huhtik. 2022
Palkinto: Palkinnot ja kunnianosoitukset