@inproceedings{haering-etal-2021-forum,
title = "Forum 4.0: An Open-Source User Comment Analysis Framework",
author = {Haering, Marlo and
Andersen, Jakob Smedegaard and
Biemann, Chris and
Loosen, Wiebke and
Milde, Benjamin and
Pietz, Tim and
St{\"o}cker, Christian and
Wiedemann, Gregor and
Zukunft, Olaf and
Maalej, Walid},
editor = "Gkatzia, Dimitra and
Seddah, Djam{\'e}",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-demos.8",
doi = "10.18653/v1/2021.eacl-demos.8",
pages = "63--70",
abstract = "With the increasing number of user comments in diverse domains, including comments on online journalism and e-commerce websites, the manual content analysis of these comments becomes time-consuming and challenging. However, research showed that user comments contain useful information for different domain experts, which is thus worth finding and utilizing. This paper introduces Forum 4.0, an open-source framework to semi-automatically analyze, aggregate, and visualize user comments based on labels defined by domain experts. We demonstrate the applicability of Forum 4.0 with comments analytics scenarios within the domains of online journalism and app stores. We outline the underlying container architecture, including the web-based user interface, the machine learning component, and the task manager for time-consuming tasks. We finally conduct machine learning experiments with simulated annotations and different sampling strategies on existing datasets from both domains to evaluate Forum 4.0{'}s performance. Forum 4.0 achieves promising classification results (ROC-AUC {\mbox{$\geq$}} 0.9 with 100 annotated samples), utilizing transformer-based embeddings with a lightweight logistic regression model. We explain how Forum 4.0{'}s architecture is applicable for millions of user comments in real-time, yet at feasible training and classification costs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haering-etal-2021-forum">
<titleInfo>
<title>Forum 4.0: An Open-Source User Comment Analysis Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Haering</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="given">Smedegaard</namePart>
<namePart type="family">Andersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiebke</namePart>
<namePart type="family">Loosen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Milde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Pietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Stöcker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregor</namePart>
<namePart type="family">Wiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olaf</namePart>
<namePart type="family">Zukunft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Maalej</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Gkatzia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the increasing number of user comments in diverse domains, including comments on online journalism and e-commerce websites, the manual content analysis of these comments becomes time-consuming and challenging. However, research showed that user comments contain useful information for different domain experts, which is thus worth finding and utilizing. This paper introduces Forum 4.0, an open-source framework to semi-automatically analyze, aggregate, and visualize user comments based on labels defined by domain experts. We demonstrate the applicability of Forum 4.0 with comments analytics scenarios within the domains of online journalism and app stores. We outline the underlying container architecture, including the web-based user interface, the machine learning component, and the task manager for time-consuming tasks. We finally conduct machine learning experiments with simulated annotations and different sampling strategies on existing datasets from both domains to evaluate Forum 4.0’s performance. Forum 4.0 achieves promising classification results (ROC-AUC \geq 0.9 with 100 annotated samples), utilizing transformer-based embeddings with a lightweight logistic regression model. We explain how Forum 4.0’s architecture is applicable for millions of user comments in real-time, yet at feasible training and classification costs.</abstract>
<identifier type="citekey">haering-etal-2021-forum</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-demos.8</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-demos.8</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>63</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Forum 4.0: An Open-Source User Comment Analysis Framework
%A Haering, Marlo
%A Andersen, Jakob Smedegaard
%A Biemann, Chris
%A Loosen, Wiebke
%A Milde, Benjamin
%A Pietz, Tim
%A Stöcker, Christian
%A Wiedemann, Gregor
%A Zukunft, Olaf
%A Maalej, Walid
%Y Gkatzia, Dimitra
%Y Seddah, Djamé
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F haering-etal-2021-forum
%X With the increasing number of user comments in diverse domains, including comments on online journalism and e-commerce websites, the manual content analysis of these comments becomes time-consuming and challenging. However, research showed that user comments contain useful information for different domain experts, which is thus worth finding and utilizing. This paper introduces Forum 4.0, an open-source framework to semi-automatically analyze, aggregate, and visualize user comments based on labels defined by domain experts. We demonstrate the applicability of Forum 4.0 with comments analytics scenarios within the domains of online journalism and app stores. We outline the underlying container architecture, including the web-based user interface, the machine learning component, and the task manager for time-consuming tasks. We finally conduct machine learning experiments with simulated annotations and different sampling strategies on existing datasets from both domains to evaluate Forum 4.0’s performance. Forum 4.0 achieves promising classification results (ROC-AUC \geq 0.9 with 100 annotated samples), utilizing transformer-based embeddings with a lightweight logistic regression model. We explain how Forum 4.0’s architecture is applicable for millions of user comments in real-time, yet at feasible training and classification costs.
%R 10.18653/v1/2021.eacl-demos.8
%U https://aclanthology.org/2021.eacl-demos.8
%U https://doi.org/10.18653/v1/2021.eacl-demos.8
%P 63-70
Markdown (Informal)
[Forum 4.0: An Open-Source User Comment Analysis Framework](https://aclanthology.org/2021.eacl-demos.8) (Haering et al., EACL 2021)
ACL
- Marlo Haering, Jakob Smedegaard Andersen, Chris Biemann, Wiebke Loosen, Benjamin Milde, Tim Pietz, Christian Stöcker, Gregor Wiedemann, Olaf Zukunft, and Walid Maalej. 2021. Forum 4.0: An Open-Source User Comment Analysis Framework. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 63–70, Online. Association for Computational Linguistics.