Search Results
Collaborative annotation and semantic enrichment of 3D media
A new FOSS (free and open source software) toolchain and associated workflow is being developed in the context of NFDI4Culture, a German consortium of research- and cultural heritage institutions working towards a shared infrastructure for research data that meets the needs of 21st century data creators, maintainers and end users across the broad spectrum of the digital libraries and archives field, and the digital humanities. This short paper and demo present how the integrated toolchain connects: 1) OpenRefine - for data reconciliation and batch upload; 2) Wikibase - for linked open data (LOD) storage; and 3) Kompakkt - for rendering and annotating 3D models. The presentation is aimed at librarians, digital curators and data managers interested in learning how to manage research datasets containing 3D media, and how to make them available within an open data environment with 3D-rendering and collaborative annotation features.
On the Impact of Features and Classifiers for Measuring Knowledge Gain during Web Search - A Case Study
Search 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.
Crowdsourcing Scholarly Discourse Annotations
The number of scholarly publications grows steadily every year and it becomes harder to find, assess and compare scholarly knowledge effectively. Scholarly knowledge graphs have the potential to address these challenges. However, creating such graphs remains a complex task. We propose a method to crowdsource structured scholarly knowledge from paper authors with a web-based user interface supported by artificial intelligence. The interface enables authors to select key sentences for annotation. It integrates multiple machine learning algorithms to assist authors during the annotation, including class recommendation and key sentence highlighting. We envision that the interface is integrated in paper submission processes for which we define three main task requirements: The task has to be . We evaluated the interface with a user study in which participants were assigned the task to annotate one of their own articles. With the resulting data, we determined whether the participants were successfully able to perform the task. Furthermore, we evaluated the interface’s usability and the participant’s attitude towards the interface with a survey. The results suggest that sentence annotation is a feasible task for researchers and that they do not object to annotate their articles during the submission process.
SHACL Constraint Validation during SPARQL Query Processing
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.
Combining Textual Features for the Detection of Hateful and Offensive Language
The 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.
On the Role of Images for Analyzing Claims in Social Media
Fake 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.
OEKG: The Open Event Knowledge Graph
Accessing and understanding contemporary and historical events of global impact such as the US elections and the Olympic Games is a major prerequisite for cross-lingual event analytics that investigate event causes, perception and consequences across country borders. In this paper, we present the Open Event Knowledge Graph (OEKG), a multilingual, event-centric, temporal knowledge graph composed of seven different data sets from multiple application domains, including question answering, entity recommendation and named entity recognition. These data sets are all integrated through an easy-to-use and robust pipeline and by linking to the event-centric knowledge graph EventKG. We describe their common schema and demonstrate the use of the OEKG at the example of three use cases: type-specific image retrieval, hybrid question answering over knowledge graphs and news articles, as well as language-specific event recommendation. The OEKG and its query endpoint are publicly available.
Meetings and Mood-Related or Not? Insights from Student Software Projects
[Background:] Teamwork, coordination, and communication are a prerequisite for the timely completion of a software project. Meetings as a facilitator for coordination and communication are an established medium for information exchange. Analyses of meetings in software projects have shown that certain interactions in these meetings, such as proactive statements followed by supportive ones, influence the mood and motivation of a team, which in turn affects its productivity. So far, however, research has focused only on certain interactions at a detailed level, requiring a complex and fine-grained analysis of a meeting itself. [Aim:] In this paper, we investigate meetings from a more abstract perspective, focusing on the polarity of the statements, i.e., whether they appear to be positive, negative, or neutral. [Method:] We analyze the relationship between the polarity of statements in meetings and different social aspects, including conflicts as well as the mood before and after a meeting. [Results:] Our results emerge from 21 student software project meetings and show some interesting insights: (1) Positive mood before a meeting is both related to the amount of positive statements in the beginning, as well as throughout the whole meeting, (2) negative mood before the meeting only influences the amount of negative statements in the first quarter of the meeting, but not the whole meeting, and (3) the amount of positive and negative statements during the meeting has no influence on the mood afterwards. [Conclusions:] We conclude that the behaviour in meetings might rather influence short-term emotional states (feelings) than long-term emotional states (mood), which are more important for the project.
A Multimodal Approach for Semantic Patent Image Retrieval
Patent images such as technical drawings contain valuable information and are frequently used by experts to compare patents. However, current approaches to patent information retrieval are largely focused on textual information. Consequently, we review previous work on patent retrieval with a focus on illustrations in figures. In this paper, we report on work in progress for a novel approach for patent image retrieval that uses deep multimodal features. Scene text spotting and optical character recognition are employed to extract numerals from an image to subsequently identify references to corresponding sentences in the patent document. Furthermore, we use a neural state-of-the-art CLIP model to extract structural features from illustrations and additionally derive textual features from the related patent text using a sentence transformer model. To fuse our multimodal features for similarity search we apply re-ranking according to averaged or maximum scores. In our experiments, we compare the impact of different modalities on the task of similarity search for patent images. The experimental results suggest that patent image retrieval can be successfully performed using the proposed feature sets, while the best results are achieved when combining the features of both modalities.