Web-based learning is evolving rapidly as traditional search engines are complemented by Large Language Models (LLMs) and other AI technologies. This evolution offers new opportunities, such as automated information synthesis and personalized learning experiences. However, this also presents new challenges, including the need for learners to be aware of potential biases and misinformation in AI-generated content, and to maintain focus and depth in their learning journeys.

Identifying the regions of a learning resource that a learner pays attention to is crucial for assessing the material's impact and improving its design and related support systems. Saliency detection in videos addresses the automatic recognition of attention-drawing regions in single frames. In educational settings, the recognition of pertinent regions in a video's visual stream can enhance content accessibility and information retrieval tasks such as video segmentation, navigation, and summarization. Such advancements can pave the way for the development of advanced AI-assisted technologies that support learning with greater efficacy. However, this task becomes particularly challenging for educational videos due to the combination of unique characteristics such as text, voice, illustrations, animations, and more. To the best of our knowledge, there is currently no study that evaluates saliency detection approaches in educational videos. In this paper, we address this gap by evaluating four state-of-the-art saliency detection approaches for educational videos. We reproduce the original studies and explore the replication capabilities for general-purpose (non-educational) datasets. Then, we investigate the generalization capabilities of the models and evaluate their performance on educational videos. We conduct a comprehensive analysis to identify common failure scenarios and possible areas of improvement. Our experimental results show that educational videos remain a challenging context for generic video saliency detection models.

Recommendation services for journals help scientists choose appropriate publication venues for their research results. They often use a semantic matching process to compare e.g. an abstract against already published articles. As these services can guide a researcher’s decision, their fairness and neutrality are critical qualities. However, the impact of journal characteristics (such as the abstract length) on recommendations is understudied. In this paper, we investigate whether editorial journal characteristics can lead to biased rankings from recommendation services, i.e. if editorial choices can systematically lead to a better ranking of one’s own journal. The performed experiments show that longer abstracts or a higher number of articles per journal can boost the rank of a journal in the recommendations. We apply these insights to an active, open-source journal recommendation system. The adaptation of the algorithm leads to an increased accuracy for smaller journals.

Today’s search engines allow users to discover relevant information in different types of modalities or media, e.g., web pages, text documents, images, or videos. It is, however, a challenging task to present mixed-modality result lists in an effective and easy-to-skim form. The two most commonly used approaches are to present the modalities side-by-side, each in a separate column of the result page; or to separate the modalities into multiple tabs. However, the field lacks a structured investigation on how the column or tab layout influence the users’ perception and usage of multimodal resources in an academic search task. In this paper, we present a user study (N=50) where the participants were asked to accomplish a search task for a fictive computer science seminar at the university. We evaluate the influence of the different layouts on (1) user search behavior (e.g., time until first resource is saved) and (2) the relevance of the selected resources for the task at hand. Finally, we discuss the results and possible implications for the design of multimodal search result presentation.

The emerging research field Search as Learning (SAL) 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.

Abstract Finding a suitable open access journal to publish scientific work is a complex task: Researchers have to navigate a constantly growing number of journals, institutional agreements with publishers, funders’ conditions and the risk of Predatory Publishers. To help with these challenges, we introduce a web-based journal recommendation system called B!SON. It is developed based on a systematic requirements analysis, built on open data, gives publisher-independent recommendations and works across domains. It suggests open access journals based on title, abstract and references provided by the user. The recommendation quality has been evaluated using a large test set of 10,000 articles. Development by two German scientific libraries ensures the longevity of the project.

Since its inception, the World Wide Web has become a major information source, consulted for a diversity of informational tasks. With an abundance of information available online, Web search engines have been a main entry point, supporting users in finding suitable Web content for ever more complex information needs. The IWILDS workshop series invites research on complex search activities related to human learning. It provides an interdisciplinary platform for the presentation and discussion of recent research on human learning on the Web, welcoming perspectives from computer & information science, education and psychology.

Web search is one of the most ubiquitous online activities and often used as a starting point to learn, i. e., to acquire or extend one's knowledge about certain topics or procedures. When learning by searching the Web, individuals are confronted with an unprecedented amount of information in various forms and varying quality. Thus, successful learning on the Web requires high degrees of self-regulation and should be supported by the adequate design of search, recommendation, and training tools. This creates a highly interdisciplinary research area at the intersection of information retrieval, human-computer interaction, psychology, and educational sciences. Search as Learning (SAL) research examines the relationships between querying, navigation, media consumption behavior, and the learning outcomes during Web search, how they can be measured, predicted, and supported.

Web search is one of the most ubiquitous online activities and often used for learning purposes, i.e., to extend one's knowledge or skills about certain topics or procedures. The importance of learning as an outcome of Web search has been recognized in research at the intersection of information retrieval, human-computer interaction, psychology, and educational sciences. Search as Learning (SAL) research examines relationships between querying, navigation, and reading behavior during Web search and the resulting learning outcomes, and how they can be measured, predicted, and supported. IWILDS aims to provide a platform to the interdisciplinary SAL community, with the objective to bring together interested researchers, provide room for presentation and discussion of novel research insights, and to inspire future directions of SAL research.

We examine the novel task of domain-independent scientific concept extraction from abstracts of scholarly articles and present two contributions. First, we suggest a set of generic scientific concepts that have been identified in a systematic annotation process. This set of concepts is utilised to annotate a corpus of scientific abstracts from 10 domains of Science, Technology and Medicine at the phrasal level in a joint effort with domain experts. The resulting dataset is used in a set of benchmark experiments to (a) provide baseline performance for this task, (b) examine the transferability of concepts between domains. Second, we present a state-of-the-art deep learning baseline. Further, we propose the active learning strategy for an optimal selection of instances from among the various domains in our data. The experimental results show that (1) a substantial agreement is achievable by non-experts after consultation with domain experts, (2) the baseline system achieves a fairly high F1 score, (3) active learning enables us to nearly halve the amount of required training data.

The Web has developed to the biggest source of information and entertainment in the world. By its size, its adaptability and flexibility, it challenged our current paradigms on information sharing in several areas. By offering everybody the opportunity to release own contents in a fast and cheap way, the Web already led to a revolution of the traditional publishing world and just now, it commences to change the perspective on advertisements. With the possibility to adapt the contents displayed on a page dynamically based on the viewer's context, campaigns launched to target rough customer groups will become an element of the past. However, this new ecosystem, that relates advertisements with the user, heavily relies on the quality of the underlying user profile. This profile has to be able to model any combination of user characteristics, the relations between its composing elements and the uncertainty that stems from the automated processing of real-world data. The work at hand describes the beginnings of a PhD project that aims to tackle those issues using a combination of data analysis, ontology engineering and processing of big data resources provided by an industrial partner. The final goal is to automatically construct and populate a profile ontology for each user identified by the system. This allows to associate these users to high-value audience segments in order to drive digital marketing.