‘Review bombing’ (RB) is a jargon referring to coordinated groups of people performing sabotage of a recommender system, e.g., submitting extreme scores. RB is conceptually alike to fake news or ‘botting’ on social media. The Last of Us Part II (TLOU2) is a survival horror videogame. It performed well under many rating metrics (e.g., Amazon’s ratings from customers) since the publication day. However, in the platform metacritic.com, where it became also the most rated item, negative ratings outnumbered positive ones. By consensus, this was the widest case of RB on a single product. Contextual literature suggests a connection with political controversies over the videogame industry (i.e., #GamerGate). For each of approx. 65k different users having reviewed TLOU2 on metacritic.com in the first 40 days from the publication date, we scraped their review (i.e., text, score, and date) and other information about their history as reviewers. Many users submitted the review in the early days and significant differences in sentiment were observed among linguistic groups. Focusing on the largest English corpus of reviews (approx. 51k), we developed methods to identify relevant patterns, anomalies, and suspicious contents. We identified and quantified major topics (Politics, LGTBQ, boycott, etc.) under discussions. Through results, we argue for the existence of a quantifiable ‘inverse effect’ of RB, where negative reviews do fuel future positive reviews (and vice-versa) due to the inherent complexity of public opinion’s dynamics.

Complex Features in Review Bombing

Venera Tomaselli
Primo
;
Giulio Giacomo Cantone
Secondo
;
Valeria Mazzeo
Ultimo
2020-01-01

Abstract

‘Review bombing’ (RB) is a jargon referring to coordinated groups of people performing sabotage of a recommender system, e.g., submitting extreme scores. RB is conceptually alike to fake news or ‘botting’ on social media. The Last of Us Part II (TLOU2) is a survival horror videogame. It performed well under many rating metrics (e.g., Amazon’s ratings from customers) since the publication day. However, in the platform metacritic.com, where it became also the most rated item, negative ratings outnumbered positive ones. By consensus, this was the widest case of RB on a single product. Contextual literature suggests a connection with political controversies over the videogame industry (i.e., #GamerGate). For each of approx. 65k different users having reviewed TLOU2 on metacritic.com in the first 40 days from the publication date, we scraped their review (i.e., text, score, and date) and other information about their history as reviewers. Many users submitted the review in the early days and significant differences in sentiment were observed among linguistic groups. Focusing on the largest English corpus of reviews (approx. 51k), we developed methods to identify relevant patterns, anomalies, and suspicious contents. We identified and quantified major topics (Politics, LGTBQ, boycott, etc.) under discussions. Through results, we argue for the existence of a quantifiable ‘inverse effect’ of RB, where negative reviews do fuel future positive reviews (and vice-versa) due to the inherent complexity of public opinion’s dynamics.
2020
978-886629-051-3
review bombing, data mining, crowd-rating systems, The Last of Us Part II
File in questo prodotto:
File Dimensione Formato  
2020_TOMASELLI V., Cantone, Mazzeo_DS&SR 2020.pdf

solo gestori archivio

Descrizione: Articolo principale
Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.04 MB
Formato Adobe PDF
1.04 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/489255
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact