=Paper=
{{Paper
|id=Vol-2758/OHARS-invited2
|storemode=property
|title=Moderation Meets Recommendation: Perspectives on the Role of Policies in Harm-Aware Recommender Ecosystems - Abstract
|pdfUrl=https://ceur-ws.org/Vol-2758/OHARS-invited2.pdf
|volume=Vol-2758
|authors=Martha Larson
|dblpUrl=https://dblp.org/rec/conf/recsys/Larson20
}}
==Moderation Meets Recommendation: Perspectives on the Role of Policies in Harm-Aware Recommender Ecosystems - Abstract==
<pdf width="1500px">https://ceur-ws.org/Vol-2758/OHARS-invited2.pdf</pdf>
<pre>
Moderation Meets Recommendation: Perspectives
on the Role of Policies in Harm-Aware Recommender
Ecosystems - Abstract
Martha Larsona
a
    Radboud University, Netherlands


                                         Abstract
                                         Behind a recommender system is the policy of the platform that runs it, which specifies acceptable system
                                         output and behavior. Policy is the language in which we communicate in order to reach consensus
                                         on what constitutes a harm-aware recommender system, and the measuring stick that allows us to
                                         enforce that consensus completely and consistently. Recently, policy has come to the forefront, as
                                         mainstream newspapers report that companies with large online platforms are limiting harmful items
                                         (YouTube) or removing items completely from their collection (Amazon). This talk discusses ways in
                                         which recommender systems can use algorithms to more closely connect with policies, allowing for
                                         better oversight and enabling harm-aware recommender systems. Our main example is a case study
                                         from bol.com, the largest e-commerce company in the Netherlands. At bol.com, policy enforcement is
                                         the responsibility of a quality team, who monitor the items that are offered by third party vendors on the
                                         platform. We discuss the promise and problems of data programming, a hybrid human-AI paradigm, to
                                         enforce policy at large scale and change its enforcement quickly in response to policy updates. This talk
                                         aims to provide an interesting perspective on the relevance and potential of policy-related recommender
                                         system research.

                                         Keywords
                                         Policy enforcement, moderation, e-commerce




Biographical Sketch
Dr. Martha Larson works in the area of multimedia retrieval and recommendation with a
focus on speech, language and meaning. She is an expert in multimedia analysis techniques
that make use of automatic speech recognition and audio analysis. Her more recent work
involves multimedia in social networks and human computation, including crowdsourcing.
She is co-founder of the MediaEval international multimedia benchmarking initiative. In 2012
and 2013, she served as Area Chair in Crowdsourcing for Multimedia at ACM Multimedia.
She has been involved in the organization of multiple workshops including: Crowdsourcing
for Multimedia (ACM Multimedia 2012 and 2013) and Searching Spontaneous Conversational
Speech (SIGIR 2008, ACM Multimedia 2009-2010).




OHARS’20: Workshop on Online Misinformation- and Harm-Aware Recommender Systems, September 25, 2020, Virtual
Event
                                       © 2020 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
    CEUR
    Workshop
    Proceedings
                  http://ceur-ws.org
                  ISSN 1613-0073
                                       CEUR Workshop Proceedings (CEUR-WS.org)



                                                                                                           3

</pre>