Institution profile

Leibniz University Hannover

Academic institutioneurope · de
Official website
Research library297linked papers
Opportunities0open roles
Selected work

Representative Papers

Sentiment analysis tools in software engineering: A systematic mapping study

Jul 01, 2022Information and Software Technology

This study addresses the growing need for emotion recognition in software development teams by systematically investigating the suitability of sentiment analysis tools for software engineering contexts. Following the PRISMA guidelines, we conducted a systematic mapping study, screening and analyzing 138 primary studies to establish— for the first time—the first comprehensive taxonomy of sentiment analysis tools spanning the entire software engineering lifecycle. The taxonomy identifies seven tool categories and five prototypical application scenarios (e.g., requirements engineering, code review), revealing critical gaps in scenario-specific adaptability, empirical validation, and cross-lifecycle support. Our key contributions are: (1) a novel, practice-oriented classification framework for sentiment analysis tools in software engineering; (2) clearly defined evaluation dimensions and applicability boundaries; and (3) an actionable research roadmap to guide both researchers and practitioners. This work provides theoretical foundations and practical guidance for project managers selecting and deploying sentiment analysis tools effectively.

19 citationsRead paper

Morphological Synthesizer for Ge’ez Language: Addressing Morphological Complexity and Resource Limitations

Sep 24, 2025RAIL

Ge’ez, a highly inflectional Classical Semitic language, suffers from severe scarcity of annotated morphological data. To address this low-resource challenge, this work introduces the first rule-based morphological synthesizer for Ge’ez augmented with Transformation Learning (TLM). The system covers all verbal inflectional paradigms using a lexicon of 1,102 verbs and accurately generates surface forms from lexical roots. Unlike data-hungry statistical approaches, it combines interpretable linguistic rules with TLM-driven optimization to maximize generalization under minimal supervision. Evaluated on a standard test set, the synthesizer achieves 97.4% accuracy—substantially outperforming baseline models. This work establishes the first publicly available morphological synthesizer for Ge’ez, filling a critical gap in Ge’ez NLP tooling. Moreover, its hybrid rule–learning methodology provides a reusable, extensible framework for morphological analysis of other low-resource classical languages.

2 citationsRead paper

Vibro-Sense: Robust Vibration-based Impulse Response Localization and Trajectory Tracking for Robotic Hands

Jan 28, 2026

This work addresses the challenge of achieving high-precision, whole-body contact perception in robots, which is hindered by the high cost and integration complexity of conventional tactile skins. The authors propose a low-cost alternative by deploying an array of piezoelectric microphones on a robotic hand and leveraging an Audio Spectrogram Transformer to decode contact location and trajectory from vibration signals. They demonstrate for the first time that complex contact dynamics—including material-dependent effects on localization and trajectory—can be effectively inferred from simple vibrational cues alone. The system achieves robust perception even during active robot motion, with static localization errors below 5 mm while maintaining high tracking accuracy under dynamic conditions. The code and dataset are publicly released to support further research.

1 citationsRead paper

Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content

Jan 08, 2026International Conference on Theory and Practice of Digital Libraries

This study addresses the conflation of citation intent and cited content type in existing citation classification methods, which hinders both fine-grained distinction and classification reliability. To resolve this, the authors propose SOFT, a novel framework grounded in semantic role theory that decouples citation intent and content type into an orthogonal two-dimensional classification scheme, establishing clear and reusable annotation guidelines. Through manual re-annotation of the ACL-ARC dataset and the creation of a cross-disciplinary ACT2 test set, the authors evaluate SOFT using both zero-shot and fine-tuned large language models. Results demonstrate that SOFT significantly outperforms existing frameworks such as ACL-ARC and SciCite in enhancing agreement between human annotators and models, improving classification performance, and enabling robust cross-domain generalization.

1 citationsRead paper

Multi-Disciplinary Dataset Discovery from Citation-Verified Literature Contexts

Dec 15, 2025ACM/IEEE Joint Conference on Digital Libraries

This work proposes a novel dataset discovery framework that leverages citation contexts from scientific papers to better capture the semantic intent behind research queries, addressing the limitations of existing dataset search engines that rely primarily on metadata and keyword matching and consequently suffer from low recall. By treating citation context as the core signal—combined with large-scale context extraction, large language model–guided pattern recognition, and provenance-preserving entity resolution—the approach significantly reduces dependence on incomplete or inconsistent metadata. Evaluated on eight computer science queries, the method achieves an average normalized recall of 47.47% (peaking at 81.82%), substantially outperforming Google Dataset Search and DataCite Commons. The framework’s novelty and practical utility have been affirmed by domain experts across multiple disciplines.

1 citationsRead paper
Recent publications

Latest Papers