arXiv subjects

Stefan Dietze

Publications and source records attributed to Stefan Dietze.

At least 37 records · Page 2Linked to original sources

arXiv2023

Large Language Models and Knowledge Graphs: Opportunities and Challenges

Large Language Models (LLMs) have taken Knowledge Representation -- and the world -- by storm. This inflection point marks a shift from explicit knowledge representation to a renewed focus on the hybrid representation of both explicit knowledge and parametric knowledge. In this position paper, we will discuss some of the common debate points within the community on LLMs (parametric knowledge) and Knowledge Graphs (explicit knowledge) and speculate on opportunities and visions that the renewed focus brings, as well as related research topics and challenges.

cs.AI↗

arXiv2023

Investigating the contribution of author- and publication-specific features to scholars' h-index prediction

Evaluation of researchers' output is vital for hiring committees and funding bodies, and it is usually measured via their scientific productivity, citations, or a combined metric such as h-index. Assessing young researchers is more critical because it takes a while to get citations and increment of h-index. Hence, predicting the h-index can help to discover the researchers' scientific impact. In addition, identifying the influential factors to predict the scientific impact is helpful for researchers seeking solutions to improve it. This study investigates the effect of author, paper and venue-specific features on the future h-index. For this purpose, we used machine learning methods to predict the h-index and feature analysis techniques to advance the understanding of feature impact. Utilizing the bibliometric data in Scopus, we defined and extracted two main groups of features. The first relates to prior scientific impact, and we name it 'prior impact-based features' and includes the number of publications, received citations, and h-index. The second group is 'non-impact-based features' and contains the features related to author, co-authorship, paper, and venue characteristics. We explored their importance in predicting h-index for researchers in three different career phases. Also, we examine the temporal dimension of predicting performance for different feature categories to find out which features are more reliable for long- and short-term prediction. We referred to the gender of the authors to examine the role of this author's characteristics in the prediction task. Our findings showed that gender has a very slight effect in predicting the h-index. We found that non-impact-based features are more robust predictors for younger scholars than seniors in the short term. Also, prior impact-based features lose their power to predict more than other features in the long-term.

cs.DL↗

arXiv2023

Which Factors are associated with Open Access Publishing? A Springer Nature Case Study

Open Access (OA) facilitates access to articles. But, authors or funders often must pay the publishing costs preventing authors who do not receive financial support from participating in OA publishing and citation advantage for OA articles. OA may exacerbate existing inequalities in the publication system rather than overcome them. To investigate this, we studied 522,411 articles published by Springer Nature. Employing correlation and regression analyses, we describe the relationship between authors affiliated with countries from different income levels, their choice of publishing model, and the citation impact of their papers. A machine learning classification method helped us to explore the importance of different features in predicting the publishing model. The results show that authors eligible for APC waivers publish more in gold-OA journals than others. In contrast, authors eligible for an APC discount have the lowest ratio of OA publications, leading to the assumption that this discount insufficiently motivates authors to publish in gold-OA journals. We found a strong correlation between the journal rank and the publishing model in gold-OA journals, whereas the OA option is mostly avoided in hybrid journals. Also, results show that the countries' income level, seniority, and experience with OA publications are the most predictive factors for OA publishing in hybrid journals.

cs.DL↗

arXiv2022

SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse

Scientific topics, claims and resources are increasingly debated as part of online discourse, where prominent examples include discourse related to COVID-19 or climate change. This has led to both significant societal impact and increased interest in scientific online discourse from various disciplines. For instance, communication studies aim at a deeper understanding of biases, quality or spreading pattern of scientific information whereas computational methods have been proposed to extract, classify or verify scientific claims using NLP and IR techniques. However, research across disciplines currently suffers from both a lack of robust definitions of the various forms of science-relatedness as well as appropriate ground truth data for distinguishing them. In this work, we contribute (a) an annotation framework and corresponding definitions for different forms of scientific relatedness of online discourse in Tweets, (b) an expert-annotated dataset of 1261 tweets obtained through our labeling framework reaching an average Fleiss Kappa $κ$ of 0.63, (c) a multi-label classifier trained on our data able to detect science-relatedness with 89% F1 and also able to detect distinct forms of scientific knowledge (claims, references). With this work we aim to lay the foundation for developing and evaluating robust methods for analysing science as part of large-scale online discourse.

cs.CL↗

arXiv2022

Still Haven't Found What You're Looking For -- Detecting the Intent of Web Search Missions from User Interaction Features

Web search is among the most frequent online activities. Whereas traditional information retrieval techniques focus on the information need behind a user query, previous work has shown that user behaviour and interaction can provide important signals for understanding the underlying intent of a search mission. An established taxonomy distinguishes between transactional, navigational and informational search missions, where in particular the latter involve a learning goal, i.e. the intent to acquire knowledge about a particular topic. We introduce a supervised approach for classifying online search missions into either of these categories by utilising a range of features obtained from the user interactions during an online search mission. Applying our model to a dataset of real-world query logs, we show that search missions can be categorised with an average F1 score of 63% and accuracy of 69%, while performance on informational and navigational missions is particularly promising (F1>75%). This suggests the potential to utilise such supervised classification during online search to better facilitate retrieval and ranking as well as to improve affiliated services, such as targeted online ads.

cs.IR↗

arXiv2022

The many facets of academic mobility and its impact on scholars' career

International mobility in academia can enhance the human and social capital of researchers and consequently their scientific outcome. However, there is still a very limited understanding of the different mobility patterns among scholars with various socio-demographic characteristics. The aim of this study is twofold. First, we investigate to what extent individual factors associate with the mobility of researchers. Second, we explore the relationship between mobility and scientific activity and impact. For this purpose, we used a bibliometric approach to track the mobility of authors. To compare the scientific outcomes of researchers, we considered the number of publications and received citations as indicators, as well as the number of unique co-authors in all their publications. We also analysed the co-authorship network of researchers and compared centrality measures of mobile and non-mobile researchers. Results show that researchers from North America and Sub-Saharan Africa, particularly female ones, have the lowest, respectively, highest tendency towards international mobility. Having international co-authors increases the probability of international movement. Our findings uncover gender inequality in international mobility across scientific fields and countries. Across genders, researchers in the Physical sciences have the most and in the Social sciences the least rate of mobility. We observed more mobility for Social scientists at the advanced career stage, while researchers in other fields prefer to move at earlier career stages. Also, we found a positive correlation between mobility and scientific outcomes, but no apparent difference between females and males. Comparing the centrality of mobile and non-mobile researchers in the co-authorship networks reveals a higher social capital advantage for mobile researchers.

cs.DL↗

arXiv2022

SaL-Lightning Dataset: Search and Eye Gaze Behavior, Resource Interactions and Knowledge Gain during Web Search

The emerging research field Search as Learning investigates how the Web facilitates learning through modern information retrieval systems. SAL research requires significant amounts of data that capture both search behavior of users and their acquired knowledge in order to obtain conclusive insights or train supervised machine learning models. However, the creation of such datasets is costly and requires interdisciplinary efforts in order to design studies and capture a wide range of features. In this paper, we address this issue and introduce an extensive dataset based on a user study, in which $114$ participants were asked to learn about the formation of lightning and thunder. Participants' knowledge states were measured before and after Web search through multiple-choice questionnaires and essay-based free recall tasks. To enable future research in SAL-related tasks we recorded a plethora of features and person-related attributes. Besides the screen recordings, visited Web pages, and detailed browsing histories, a large number of behavioral features and resource features were monitored. We underline the usefulness of the dataset by describing three, already published, use cases.

cs.IR↗

arXiv2021

SoMeSci- A 5 Star Open Data Gold Standard Knowledge Graph of Software Mentions in Scientific Articles

Knowledge about software used in scientific investigations is important for several reasons, for instance, to enable an understanding of provenance and methods involved in data handling. However, software is usually not formally cited, but rather mentioned informally within the scholarly description of the investigation, raising the need for automatic information extraction and disambiguation. Given the lack of reliable ground truth data, we present SoMeSci (Software Mentions in Science) a gold standard knowledge graph of software mentions in scientific articles. It contains high quality annotations (IRR: $κ{=}.82$) of 3756 software mentions in 1367 PubMed Central articles. Besides the plain mention of the software, we also provide relation labels for additional information, such as the version, the developer, a URL or citations. Moreover, we distinguish between different types, such as application, plugin or programming environment, as well as different types of mentions, such as usage or creation. To the best of our knowledge, SoMeSci is the most comprehensive corpus about software mentions in scientific articles, providing training samples for Named Entity Recognition, Relation Extraction, Entity Disambiguation, and Entity Linking. Finally, we sketch potential use cases and provide baseline results.

cs.IR↗

arXiv2021

Predicting Knowledge Gain during Web Search based on Multimedia Resource Consumption

In informal learning scenarios the popularity of multimedia content, such as video tutorials or lectures, has significantly increased. Yet, the users' interactions, navigation behavior, and consequently learning outcome, have not been researched extensively. Related work in this field, also called search as learning, has focused on behavioral or text resource features to predict learning outcome and knowledge gain. In this paper, we investigate whether we can exploit features representing multimedia resource consumption to predict of knowledge gain (KG) during Web search from in-session data, that is without prior knowledge about the learner. For this purpose, we suggest a set of multimedia features related to image and video consumption. Our feature extraction is evaluated in a lab study with 113 participants where we collected data for a given search as learning task on the formation of thunderstorms and lightning. We automatically analyze the monitored log data and utilize state-of-the-art computer vision methods to extract features about the seen multimedia resources. Experimental results demonstrate that multimedia features can improve KG prediction. Finally, we provide an analysis on feature importance (text and multimedia) for KG prediction.

cs.IR↗

arXiv2021

Exploiting stance hierarchies for cost-sensitive stance detection of Web documents

Fact checking is an essential challenge when combating fake news. Identifying documents that agree or disagree with a particular statement (claim) is a core task in this process. In this context, stance detection aims at identifying the position (stance) of a document towards a claim. Most approaches address this task through a 4-class classification model where the class distribution is highly imbalanced. Therefore, they are particularly ineffective in detecting the minority classes (for instance, 'disagree'), even though such instances are crucial for tasks such as fact-checking by providing evidence for detecting false claims. In this paper, we exploit the hierarchical nature of stance classes, which allows us to propose a modular pipeline of cascading binary classifiers, enabling performance tuning on a per step and class basis. We implement our approach through a combination of neural and traditional classification models that highlight the misclassification costs of minority classes. Evaluation results demonstrate state-of-the-art performance of our approach and its ability to significantly improve the classification performance of the important 'disagree' class.

cs.CL↗

arXiv2021

Better Together -- An Ensemble Learner for Combining the Results of Ready-made Entity Linking Systems

Entity linking (EL) is the task of automatically identifying entity mentions in text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. Throughout the past decade, a plethora of EL systems and pipelines have become available, where performance of individual systems varies heavily across corpora, languages or domains. Linking performance varies even between different mentions in the same text corpus, where, for instance, some EL approaches are better able to deal with short surface forms while others may perform better when more context information is available. To this end, we argue that performance may be optimised by exploiting results from distinct EL systems on the same corpus, thereby leveraging their individual strengths on a per-mention basis. In this paper, we introduce a supervised approach which exploits the output of multiple ready-made EL systems by predicting the correct link on a per-mention basis. Experimental results obtained on existing ground truth datasets and exploiting three state-of-the-art EL systems show the effectiveness of our approach and its capacity to significantly outperform the individual EL systems as well as a set of baseline methods.

cs.CL↗

arXiv2020

TweetsCOV19 -- A Knowledge Base of Semantically Annotated Tweets about the COVID-19 Pandemic

Publicly available social media archives facilitate research in the social sciences and provide corpora for training and testing a wide range of machine learning and natural language processing methods. With respect to the recent outbreak of the Coronavirus disease 2019 (COVID-19), online discourse on Twitter reflects public opinion and perception related to the pandemic itself as well as mitigating measures and their societal impact. Understanding such discourse, its evolution, and interdependencies with real-world events or (mis)information can foster valuable insights. On the other hand, such corpora are crucial facilitators for computational methods addressing tasks such as sentiment analysis, event detection, or entity recognition. However, obtaining, archiving, and semantically annotating large amounts of tweets is costly. In this paper, we describe TweetsCOV19, a publicly available knowledge base of currently more than 8 million tweets, spanning October 2019 - April 2020. Metadata about the tweets as well as extracted entities, hashtags, user mentions, sentiments, and URLs are exposed using established RDF/S vocabularies, providing an unprecedented knowledge base for a range of knowledge discovery tasks. Next to a description of the dataset and its extraction and annotation process, we present an initial analysis and use cases of the corpus.

cs.SI↗

arXiv2020

The Role of Word-Eye-Fixations for Query Term Prediction

Throughout the search process, the user's gaze on inspected SERPs and websites can reveal his or her search interests. Gaze behavior can be captured with eye tracking and described with word-eye-fixations. Word-eye-fixations contain the user's accumulated gaze fixation duration on each individual word of a web page. In this work, we analyze the role of word-eye-fixations for predicting query terms. We investigate the relationship between a range of in-session features, in particular, gaze data, with the query terms and train models for predicting query terms. We use a dataset of 50 search sessions obtained through a lab study in the social sciences domain. Using established machine learning models, we can predict query terms with comparably high accuracy, even with only little training data. Feature analysis shows that the categories Fixation, Query Relevance and Session Topic contain the most effective features for our task.

cs.IR↗

arXiv2019

A Software Framework and Datasets for the Analysis of Graph Measures on RDF Graphs

As the availability and the inter-connectivity of RDF datasets grow, so does the necessity to understand the structure of the data. Understanding the topology of RDF graphs can guide and inform the development of, e.g. synthetic dataset generators, sampling methods, index structures, or query optimizers. In this work, we propose two resources: (i) a software framework able to acquire, prepare, and perform a graph-based analysis on the topology of large RDF graphs, and (ii) results on a graph-based analysis of 280 datasets from the LOD Cloud with values for 28 graph measures computed with the framework. We present a preliminary analysis based on the proposed resources and point out implications for synthetic dataset generators. Finally, we identify a set of measures, that can be used to characterize graphs in the Semantic Web.

cs.DB↗

arXiv2019

Data4UrbanMobility: Towards Holistic Data Analytics for Mobility Applications in Urban Regions

With the increasing availability of mobility-related data, such as GPS-traces, Web queries and climate conditions, there is a growing demand to utilize this data to better understand and support urban mobility needs. However, data available from the individual actors, such as providers of information, navigation and transportation systems, is mostly restricted to isolated mobility modes, whereas holistic data analytics over integrated data sources is not sufficiently supported. In this paper we present our ongoing research in the context of holistic data analytics to support urban mobility applications in the Data4UrbanMobility (D4UM) project. First, we discuss challenges in urban mobility analytics and present the D4UM platform we are currently developing to facilitate holistic urban data analytics over integrated heterogeneous data sources along with the available data sources. Second, we present the MiC app - a tool we developed to complement available datasets with intermodal mobility data (i.e. data about journeys that involve more than one mode of mobility) using a citizen science approach. Finally, we present selected use cases and discuss our future work.

cs.CY↗

arXiv2018

Same but Different: Distant Supervision for Predicting and Understanding Entity Linking Difficulty

Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where the lack of precision on particularly ambiguous mentions often spoils the usefulness of automated disambiguation results in real applications. A priori approximations of the difficulty to link a particular entity mention can facilitate flagging of critical cases as part of semi-automated EL systems, while detecting latent factors that affect the EL performance, like corpus-specific features, can provide insights on how to improve a system based on the special characteristics of the underlying corpus. In this paper, we first introduce a consensus-based method to generate difficulty labels for entity mentions on arbitrary corpora. The difficulty labels are then exploited as training data for a supervised classification task able to predict the EL difficulty of entity mentions using a variety of features. Experiments over a corpus of news articles show that EL difficulty can be estimated with high accuracy, revealing also latent features that affect EL performance. Finally, evaluation results demonstrate the effectiveness of the proposed method to inform semi-automated EL pipelines.

cs.CL↗

arXiv2018

Time-Aware and Corpus-Specific Entity Relatedness

Entity relatedness has emerged as an important feature in a plethora of applications such as information retrieval, entity recommendation and entity linking. Given an entity, for instance a person or an organization, entity relatedness measures can be exploited for generating a list of highly-related entities. However, the relation of an entity to some other entity depends on several factors, with time and context being two of the most important ones (where, in our case, context is determined by a particular corpus). For example, the entities related to the International Monetary Fund are different now compared to some years ago, while these entities also may highly differ in the context of a USA news portal compared to a Greek news portal. In this paper, we propose a simple but flexible model for entity relatedness which considers time and entity aware word embeddings by exploiting the underlying corpus. The proposed model does not require external knowledge and is language independent, which makes it widely useful in a variety of applications.

cs.IR↗

arXiv2018

TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets

Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.

cs.IR↗