BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Elisabeth Lex

Elisabeth Lex appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Information RetrievalMachine LearningDigital LibrariesArtificial IntelligenceNeural and Evolutionary ComputingSocial and Information Networks

Catalog footprint

What is connected

12works
6topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems

LLM agents are increasingly used for personalization due to their ability to communicate directly with users in natural language, integrate external knowledge bases, and negotiate with other (possibly human) agents. Especially in multistakeholder AI systems with multiple distinct objectives, LLM agents are used to independently optimize for each stakeholder's goals. Here, stakeholder alignment is essential to identify and map these goals to provide LLM agents with quantifiable objectives. Plus, the way in which the outputs of the LLM agents are aggregated is fundamental to ensuring fair outcomes for all agents and, therefore, stakeholders. In this work, we identify open research challenges and propose a conceptual framework for designing fair multi-agent multistakeholder personalization systems that balance competing stakeholder objectives. Our framework integrates (i) methods to align stakeholder objectives and LLM agents, (ii) aggregation strategies, e.g., based on social choice theory, to form fair collective decisions, and (iii) stakeholder-centric evaluation procedures for both individual and collective agent behavior. We showcase our framework through a tourism use case and discuss possible applications in other domains, such as education and healthcare. Finally, we discuss domain-specific fairness tensions and review datasets for evaluating multistakeholder fairness and multi-agent personalization systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations

Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level, we apply DP only to the most stereotypical user data likely to reveal sensitive attributes, such as gender or age, to reduce unnecessary perturbation; we refer to this as targeted DP. At the model level, we use meta-learning to improve robustness to remaining DP-noise. This achieves a better trade-off between accuracy and privacy than standard approaches: Meta-learning improves accuracy and targeted DP leads to lower empirical privacy risk compared to uniformly applied DP and full DP baselines. Overall, our findings show that selectively applying DP at the data level together with meta-learning at the model level can effectively balance recommendation accuracy and user privacy.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Modeling Behavioral Patterns in News Recommendations Using Fuzzy Neural Networks

News recommender systems are increasingly driven by black-box models, offering little transparency for editorial decision-making. In this work, we introduce a transparent recommender system that uses fuzzy neural networks to learn human-readable rules from behavioral data for predicting article clicks. By extracting the rules at configurable thresholds, we can control rule complexity and thus, the level of interpretability. We evaluate our approach on two publicly available news datasets (i.e., MIND and EB-NeRD) and show that we can accurately predict click behavior compared to several established baselines, while learning human-readable rules. Furthermore, we show that the learned rules reveal news consumption patterns, enabling editors to align content curation goals with target audience behavior.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Empirical Comparison of Graph Embeddings for Trust-Based Collaborative Filtering

In this work, we study the utility of graph embeddings to generate latent user representations for trust-based collaborative filtering. In a cold-start setting, on three publicly available datasets, we evaluate approaches from four method families: (i) factorization-based, (ii) random walk-based, (iii) deep learning-based, and (iv) the Large-scale Information Network Embedding (LINE) approach. We find that across the four families, random-walk-based approaches consistently achieve the best accuracy. Besides, they result in highly novel and diverse recommendations. Furthermore, our results show that the use of graph embeddings in trust-based collaborative filtering significantly improves user coverage.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks

Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. In this work, we systematically study the impact of community structure on the performance of GNNs in semi-supervised node classification on graphs. Following an ablation study on six datasets, we measure the performance of GNNs on the original graphs, and the change in performance in the presence and the absence of community structure. Our results suggest that communities typically have a major impact on the learning process and classification performance. For example, in cases where the majority of nodes from one community share a single classification label, breaking up community structure results in a significant performance drop. On the other hand, for cases where labels show low correlation with communities, we find that the graph structure is rather irrelevant to the learning process, and a feature-only baseline becomes hard to beat. With our work, we provide deeper insights in the abilities and limitations of GNNs, including a set of general guidelines for model selection based on the graph structure.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Listener Modeling and Context-aware Music Recommendation Based on Country Archetypes

Music preferences are strongly shaped by the cultural and socio-economic background of the listener, which is reflected, to a considerable extent, in country-specific music listening profiles. Previous work has already identified several country-specific differences in the popularity distribution of music artists listened to. In particular, what constitutes the "music mainstream" strongly varies between countries. To complement and extend these results, the article at hand delivers the following major contributions: First, using state-of-the-art unsupervised learning techniques, we identify and thoroughly investigate (1) country profiles of music preferences on the fine-grained level of music tracks (in contrast to earlier work that relied on music preferences on the artist level) and (2) country archetypes that subsume countries sharing similar patterns of listening preferences. Second, we formulate four user models that leverage the user's country information on music preferences. Among others, we propose a user modeling approach to describe a music listener as a vector of similarities over the identified country clusters or archetypes. Third, we propose a context-aware music recommendation system that leverages implicit user feedback, where context is defined via the four user models. More precisely, it is a multi-layer generative model based on a variational autoencoder, in which contextual features can influence recommendations through a gating mechanism. Fourth, we thoroughly evaluate the proposed recommendation system and user models on a real-world corpus of more than one billion listening records of users around the world (out of which we use 369 million in our experiments) and show its merits vis-a-vis state-of-the-art algorithms that do not exploit this type of context information.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

High Enough? Explaining and Predicting Traveler Satisfaction Using Airline Review

Air travel is one of the most frequently used means of transportation in our every-day life. Thus, it is not surprising that an increasing number of travelers share their experiences with airlines and airports in form of online reviews on the Web. In this work, we thrive to explain and uncover the features of airline reviews that contribute most to traveler satisfaction. To that end, we examine reviews crawled from the Skytrax air travel review portal. Skytrax provides four review categories to review airports, lounges, airlines and seats. Each review category consists of several five-star ratings as well as free-text review content. In this paper, we conducted a comprehensive feature study and we find that not only five-star rating information such as airport queuing time and lounge comfort highly correlate with traveler satisfaction but also textual features in the form of the inferred review text sentiment. Based on our findings, we created classifiers to predict traveler satisfaction using the best performing rating features. Our results reveal that given our methodology, traveler satisfaction can be predicted with high accuracy. Additionally, we find that training a model on the sentiment of the review text provides a competitive alternative when no five star rating information is available. We believe that our work is of interest for researchers in the area of modeling and predicting user satisfaction based on available review data on the Web.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics

Classic resource recommenders like Collaborative Filtering (CF) treat users as being just another entity, neglecting non-linear user-resource dynamics shaping attention and interpretation. In this paper, we propose a novel hybrid recommendation strategy that refines CF by capturing these dynamics. The evaluation results reveal that our approach substantially improves CF and, depending on the dataset, successfully competes with a computationally much more expensive Matrix Factorization variant.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Exploring Coverage and Distribution of Identifiers on the Scholarly Web

In a scientific publishing environment that is increasingly moving online, identifiers of scholarly work are gaining in importance. In this paper, we analysed identifier distribution and coverage of articles from the discipline of quantitative biology using arXiv, Mendeley and CrossRef as data sources. The results show that when retrieving arXiv articles from Mendeley, we were able to find more papers using the DOI than the arXiv ID. This indicates that DOI may be a better identifier with respect to findability. We also find that coverage of articles on Mendeley decreases in the most recent years, whereas the coverage of DOIs does not decrease in the same order of magnitude. This hints at the fact that there is a certain time lag involved, before articles are covered in crowd-sourced services on the scholarly web.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Research Data Explored II: the Anatomy and Reception of figshare

This is the second paper in a series of bibliometric studies of research data. In this paper, we present an analysis of figshare, one of the largest multidisciplinary repositories for research materials to date. We analysed the structure of items archived in figshare, their usage, and their reception in two altmetrics sources (PlumX and ImpactStory). We found that figshare acts (1) as a personal repository for yet unpublished materials, (2) as a platform for newly published research materials, and (3) as an archive for PLOS. Depending on the function, we found different bibliometric characteristics. Items archived from PLOS tend to be coming from the natural sciences and are often unviewed and non-downloaded. Self-archived items, however, come from a variety of disciplines and exhibit some patterns of higher usage. In the altmetrics analysis, we found that Twitter was the social media service where research data gained most attention; generally, research data published in 2014 were most popular across social media services. PlumX detects considerably more items in social media and also finds higher altmetric scores than ImpactStory.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Research Data Explored: Citations versus Altmetrics

The study explores the citedness of research data, its distribution over time and how it is related to the availability of a DOI (Digital Object Identifier) in Thomson Reuters' DCI (Data Citation Index). We investigate if cited research data "impact" the (social) web, reflected by altmetrics scores, and if there is any relationship between the number of citations and the sum of altmetrics scores from various social media-platforms. Three tools are used to collect and compare altmetrics scores, i.e. PlumX, ImpactStory, and Altmetric.com. In terms of coverage, PlumX is the most helpful altmetrics tool. While research data remain mostly uncited (about 85%), there has been a growing trend in citing data sets published since 2007. Surprisingly, the percentage of the number of cited research data with a DOI in DCI has decreased in the last years. Only nine repositories account for research data with DOIs and two or more citations. The number of cited research data with altmetrics scores is even lower (4 to 9%) but shows a higher coverage of research data from the last decade. However, no correlation between the number of citations and the total number of altmetrics scores is observable. Certain data types (i.e. survey, aggregate data, and sequence data) are more often cited and receive higher altmetrics scores.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Assessing the Quality of Web Content

This paper describes our approach towards the ECML/PKDD Discovery Challenge 2010. The challenge consists of three tasks: (1) a Web genre and facet classification task for English hosts, (2) an English quality task, and (3) a multilingual quality task (German and French). In our approach, we create an ensemble of three classifiers to predict unseen Web hosts whereas each classifier is trained on a different feature set. Our final NDCG on the whole test set is 0:575 for Task 1, 0:852 for Task 2, and 0:81 (French) and 0:77 (German) for Task 3, which ranks second place in the ECML/PKDD Discovery Challenge 2010.

0 citations0 reviewsNo code linkedOpen access