arXiv subjects

Tim A. Majchrzak

Publications and source records attributed to Tim A. Majchrzak.

5 recordsLinked to original sources

arXiv2025

Defining, Understanding, and Detecting Online Toxicity: Challenges and Machine Learning Approaches

Online toxic content has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. A significant amount of research has been focused on detecting or analyzing toxic content using machine-learning approaches. The proliferation of toxic content across digital platforms has spurred extensive research into automated detection mechanisms, primarily driven by advances in machine learning and natural language processing. Overall, the present study represents the synthesis of 140 publications on different types of toxic content on digital platforms. We present a comprehensive overview of the datasets used in previous studies focusing on definitions, data sources, challenges, and machine learning approaches employed in detecting online toxicity, such as hate speech, offensive language, and harmful discourse. The dataset encompasses content in 32 languages, covering topics such as elections, spontaneous events, and crises. We examine the possibility of using existing cross-platform data to improve the performance of classification models. We present the recommendations and guidelines for new research on online toxic consent and the use of content moderation for mitigation. Finally, we present some practical guidelines to mitigate toxic content from online platforms.

cs.CL↗

arXiv2024

Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language

Hate speech has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. Multiple approaches have been developed to detect hate speech using artificial intelligence, but a generalized model is yet unaccomplished. The challenge for hate speech detection as text classification is the cost of obtaining high-quality training data. This study focuses on detecting bilingual hate speech in YouTube comments and measuring the impact of using additional data from other platforms in the performance of the classification model. We examine the value of additional training datasets from cross-platforms for improving the performance of classification models. We also included factors such as content similarity, definition similarity, and common hate words to measure the impact of datasets on performance. Our findings show that adding more similar datasets based on content similarity, hate words, and definitions improves the performance of classification models. The best performance was obtained by combining datasets from YouTube comments, Twitter, and Gab with an F1-score of 0.74 and 0.68 for English and German YouTube comments.

cs.CL↗

arXiv2020

An Exploratory Study of COVID-19 Misinformation on Twitter

During the COVID-19 pandemic, social media has become a home ground for misinformation. To tackle this infodemic, scientific oversight, as well as a better understanding by practitioners in crisis management, is needed. We have conducted an exploratory study into the propagation, authors and content of misinformation on Twitter around the topic of COVID-19 in order to gain early insights. We have collected all tweets mentioned in the verdicts of fact-checked claims related to COVID-19 by over 92 professional fact-checking organisations between January and mid-July 2020 and share this corpus with the community. This resulted in 1 500 tweets relating to 1 274 false and 276 partially false claims, respectively. Exploratory analysis of author accounts revealed that the verified twitter handle(including Organisation/celebrity) are also involved in either creating (new tweets) or spreading (retweet) the misinformation. Additionally, we found that false claims propagate faster than partially false claims. Compare to a background corpus of COVID-19 tweets, tweets with misinformation are more often concerned with discrediting other information on social media. Authors use less tentative language and appear to be more driven by concerns of potential harm to others. Our results enable us to suggest gaps in the current scientific coverage of the topic as well as propose actions for authorities and social media users to counter misinformation.

cs.SI↗

arXiv2017

On Constructing Persistent Identifiers with Persistent Resolution Targets

Persistent Identifiers (PID) are the foundation referencing digital assets in scientific publications, books, and digital repositories. In its realization, PIDs contain metadata and resolving targets in form of URLs that point to data sets located on the network. In contrast to PIDs, the target URLs are typically changing over time; thus, PIDs need continuous maintenance -- an effort that is increasing tremendously with the advancement of e-Science and the advent of the Internet-of-Things (IoT). Nowadays, billions of sensors and data sets are subject of PID assignment. This paper presents a new approach of embedding location independent targets into PIDs that allows the creation of maintenance-free PIDs using content-centric network technology and overlay networks. For proving the validity of the presented approach, the Handle PID System is used in conjunction with Magnet Link access information encoding, state-of-the-art decentralized data distribution with BitTorrent, and Named Data Networking (NDN) as location-independent data access technology for networks. Contrasting existing approaches, no green-field implementation of PID or major modifications of the Handle System is required to enable location-independent data dissemination with maintenance-free PIDs.

cs.NI↗

arXiv2010

Improving the Technical Aspects of Software Testing in Enterprises

Many software developments projects fail due to quality problems. Software testing enables the creation of high quality software products. Since it is a cumbersome and expensive task, and often hard to manage, both its technical background and its organizational implementation have to be well founded. We worked with regional companies that develop software in order to learn about their distinct weaknesses and strengths with regard to testing. Analyzing and comparing the strengths, we derived best practices. In this paper we explain the project's background and sketch the design science research methodology used. We then introduce a graphical categorization framework that helps companies in judging the applicability of recommendations. Eventually, we present details on five recommendations for tech-nical aspects of testing. For each recommendation we give im-plementation advice based on the categorization framework.

cs.SE↗