10 results
Search Results
Now showing 1 - 10 of 10
- ItemCheck square at CheckThat! 2020: Claim Detection in Social Media via Fusion of Transformer and Syntactic Features(Aachen, Germany : RWTH Aachen, 2020) Cheema, Gullasl S.; Hakimov, Sherzod; Ewerth, Ralph; Cappellato, Linda; Eickhoff, Carsten; Ferro, Nicola; Névéol, AurélieIn this digital age of news consumption, a news reader has the ability to react, express and share opinions with others in a highly interactive and fast manner. As a consequence, fake news has made its way into our daily life because of very limited capacity to verify news on the Internet by large companies as well as individuals. In this paper, we focus on solving two problems which are part of the fact-checking ecosystem that can help to automate fact-checking of claims in an ever increasing stream of content on social media. For the first prob-lem, claim check-worthiness prediction, we explore the fusion of syntac-tic features and deep transformer Bidirectional Encoder Representations from Transformers (BERT) embeddings, to classify check-worthiness of a tweet, i.e. whether it includes a claim or not. We conduct a detailed feature analysis and present our best performing models for English and Arabic tweets. For the second problem, claim retrieval, we explore the pre-trained embeddings from a Siamese network transformer model (sentence-transformers) specifically trained for semantic textual similar-ity, and perform KD-search to retrieve verified claims with respect to a query tweet.
- ItemCombining Textual Features for the Detection of Hateful and Offensive Language(Aachen, Germany : RWTH Aachen, 2021) Hakimov, Sherzod; Ewerth, Ralph; Mehta, Parth; Mandl, Thomas; Majumder, Prasenjit; Mitra, MandarThe detection of offensive, hateful and profane language has become a critical challenge since many users in social networks are exposed to cyberbullying activities on a daily basis. In this paper, we present an analysis of combining different textual features for the detection of hateful or offensive posts on Twitter. We provide a detailed experimental evaluation to understand the impact of each building block in a neural network architecture. The proposed architecture is evaluated on the English Subtask 1A: Identifying Hate, offensive and profane content from the post datasets of HASOC-2021 dataset under the team name TIB-VA. We compared different variants of the contextual word embeddings combined with the character level embeddings and the encoding of collected hate terms.
- ItemOn the Impact of Features and Classifiers for Measuring Knowledge Gain during Web Search - A Case Study(Aachen, Germany : RWTH Aachen, 2021) Gritz, Wolfgang; Hoppe, Anett; Ewerth, Ralph; Cong, Gao; Ramanath, MayaSearch engines are normally not designed to support human learning intents and processes. The ÿeld of Search as Learning (SAL) aims to investigate the characteristics of a successful Web search with a learning purpose. In this paper, we analyze the impact of text complexity of Web pages on predicting knowledge gain during a search session. For this purpose, we conduct an experimental case study and investigate the in˝uence of several text-based features and classiÿers on the prediction task. We build upon data from a study of related work, where 104 participants were given the task to learn about the formation of lightning and thunder through Web search. We perform an extensive evaluation based on a state-of-the-art approach and extend it with additional features related to textual complexity of Web pages. In contrast to prior work, we perform a systematic search for optimal hyperparameters and show the possible in˝uence of feature selection strategies on the knowledge gain prediction. When using the new set of features, state-of-the-art results are noticeably improved. The results indicate that text complexity of Web pages could be an important feature resource for knowledge gain prediction.
- ItemOn the Role of Images for Analyzing Claims in Social Media(Aachen, Germany : RWTH Aachen, 2021) Cheema, Gullal S.; Hakimov, Sherzod; Müller-Budack, Eric; Ewerth, RalphFake news is a severe problem in social media. In this paper, we present an empirical study on visual, textual, and multimodal models for the tasks of claim, claim check-worthiness, and conspiracy detection, all of which are related to fake news detection. Recent work suggests that images are more influential than text and often appear alongside fake text. To this end, several multimodal models have been proposed in recent years that use images along with text to detect fake news on social media sites like Twitter. However, the role of images is not well understood for claim detection, specifically using transformer-based textual and multimodal models. We investigate state-of-the-art models for images, text (Transformer-based), and multimodal information for four different datasets across two languages to understand the role of images in the task of claim and conspiracy detection.
- ItemTIB's visual analytics group at MediaEval '20: Detecting fake news on corona virus and 5G conspiracy(Aachen, Germany : RWTH Aachen, 2020) Cheema, Gullal S.; Hakimov, Sherzod; Ewerth, Ralph; Hicks, StevenFake news on social media has become a hot topic of research as it negatively impacts the discourse of real news in the public. Specifi-cally, the ongoing COVID-19 pandemic has seen a rise of inaccurate and misleading information due to the surrounding controversies and unknown details at the beginning of the pandemic. The Fak-eNews task at MediaEval 2020 tackles this problem by creating a challenge to automatically detect tweets containing misinformation based on text and structure from Twitter follower network. In this paper, we present a simple approach that uses BERT embeddings and a shallow neural network for classifying tweets using only text, and discuss our findings and limitations of the approach in text-based misinformation detection.
- ItemSHACL Constraint Validation during SPARQL Query Processing(Aachen, Germany : RWTH Aachen, 2021) Rohde, Phlipp D.The importance of knowledge graphs is increasing. Due to their application in more and more real-world use-cases the data quality issue has to be addressed. The Shapes Constraint Language (SHACL) is the W3C recommendation language for defining integrity constraints over knowledge graphs expressed in the Resource Description Framework (RDF). Annotating SPARQL query results with metadata from the SHACL validation provides a better understanding of the knowledge graph and its data quality. We propose a query engine that is able to efficiently evaluate which instances in the knowledge graph fulfill the requirements from the SHACL shape schema and annotate the SPARQL query result with this metadata. Hence, adding the dimension of explainability to SPARQL query processing. Our preliminary analysis shows that the proposed optimizations performed for SHACL validation during SPARQL query processing increase the performance compared to a naive approach. However, in some queries the naive approach outperforms the optimizations. This shows that more work needs to be done in this topic to fully comprehend all impacting factors and to identify the amount of overhead added to the query execution.
- ItemA Review on Recent Advances in Video-based Learning Research: Video Features, Interaction, Tools, and Technologies(Aachen, Germany : RWTH Aachen, 2021) Navarrete, Evelyn; Hoppe, Anett; Ewerth, Ralph; Cong, Gao; Ramanath, MayaHuman learning shifts stronger than ever towards online settings, and especially towards video platforms. There is an abundance of tutorials and lectures covering diverse topics, from fixing a bike to particle physics. While it is advantageous that learning resources are freely available on the Web, the quality of the resources varies a lot. Given the number of available videos, users need algorithmic support in finding helpful and entertaining learning resources. In this paper, we present a review of the recent research literature (2020-2021) on video-based learning. We focus on publications that examine the characteristics of video content, analyze frequently used features and technologies, and, finally, derive conclusions on trends and possible future research directions.
- ItemPreface of MEPDaW 2020: Managing the evolution and preservation of the data web(Aachen, Germany : RWTH Aachen, 2020) Orlandi, Fabrizio; Graux, Damien; Vidal, Maria-Esther; Fernández, Javier D.; Debattista, Jeremy; Orlandi, Fabrizio; Graux, Damien; Vidal, Maria-Esther; Fernández, Javier D.; Debattista, JeremyThe MEPDaW workshop series targets one of the emerging and fundamental problems of the Web, specifically the management and preservation of evolving knowledge graphs. During the past six years, the workshop series has been gathering a community of researchers and practitioners around these challenges. To date, the series has successfully published more than 30 articles allowing more than 50 individual authors to present and share their ideas. This 6th edition, virtually co-located with the International Semantic Web Conference (ISWC 2020), gathered the community around nine research publications and one invited keynote presentation. The event took place online on the 1st of November, 2020.
- ItemClassification of important segments in educational videos using multimodal features(Aachen, Germany : RWTH Aachen, 2020) Ghauri, Junaid Ahmed; Hakimov, Sherzod; Ewerth, Ralph; Conrad, Stefan; Tiddi, IlariaVideos are a commonly-used type of content in learning during Web search. Many e-learning platforms provide quality content, but sometimes educational videos are long and cover many topics. Humans are good in extracting important sec-tions from videos, but it remains a significant challenge for computers. In this paper, we address the problem of assigning importance scores to video segments, that is how much information they contain with respect to the overall topic of an educational video. We present an annotation tool and a new dataset of annotated educational videos collected from popular online learning platforms. Moreover, we propose a multimodal neural architecture that utilizes state-of-the-art audio, visual and textual features. Our experiments investigate the impact of visual and temporal information, as well as the combination of multimodal features on importance prediction.
- ItemDemonstration of a customizable knowledge graph visualization framework(Aachen, Germany : RWTH Aachen, 2020) Wiens, Vitali; Lohmann, Steffen; Taylor, Kerry; Gonçalves, Rafael; Lecue, Freddy; Yan, JunIn the context of the Semantic Web, various visualization methods and tools exist. However, suitable visualizations are highly de-pendent on individual use cases and targeted user groups. Therefore, existing solutions require modifications and adjustments to meet the de-mands of other use cases and user groups. In this demo, we present an approach for a unified framework addressing customizable visual rep-resentations of knowledge graphs. Our approach refines the commonly used steps in the visualization generation process (i.e., data access, map-ping to visual primitives, and rendering) for Semantic Web contexts. Separation of concerns for individual steps and a modular and customiz-able architecture build the foundation for a pipeline-based visualization framework. The framework enables the creation and selection of the right components for the right tasks, realizing a variety of use cases and visual representations in Semantic Web contexts.