Building an Integrated Comment Moderation System - Towards a Semi-Automatic Moderation tool

Riehle, Dennis M.; Niemann, Marco; Brunk, Jens; Assenmacher, Dennis; Trautmann, Heike; Becker, Jörg


Abstract

The past decade has been characterized by a strong increase in the use of social media and a continuous growth of public online discussion. With the failure of purely manual moderation, platform operators started searching for semi-automated solutions, where the application of Natural Language Processing (NLP) and Machine Learning (ML) techniques is promising. However, this requires huge financial investments for algorithmic implementations, data collection, and model training, which only big players can afford. To support smaller or medium-sized media enterprises (SME), we developed an integrated comment moderation system as an IT platform. This platform acts as a service provider and offers Analytics as a Service (AaaS) to SMEs. Operating such a platform, however, requires a robust technology stack, integrated workflows and well-defined interfaces between all parties. In this paper, we develop and discuss a suitable IT architecture and present a prototypical implementation.

Keywords
Comment moderation; Machine learning; Business model; IT platform; Analytics as a service



Publication type
Research article in proceedings (conference)

Peer reviewed
Yes

Publication status
Published

Year
2020

Conference
HCI International 2020

Venue
Copenhagen

Book title
Social Computing and Social Media. Participation, User Experience, Consumer Experience, and Applications of Social Computing. 12th International Conference, SCSM 2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Copenhagen, Denmark, July 19–24, 2020, Proceedings, Part II

Editor
Meiselwitz, Gabriele

Start page
71

End page
86

Volume
12195

Title of series
Lecture Notes in Computer Science

Publisher
Springer

Place
Cham

Language
English

ISSN
0302-9743

ISBN
978-3-030-49576-3

DOI

Full text