Dr. Stefan Gindl is a senior researcher in the Department of New Media Technology at MODUL University Vienna. He originally studied medical Informatics, but his master thesis "Negation Detection in Clinical Practice Guidelines" kindled his interest in Natural Language Processing. Text mining and artificial intelligence are his research areas since many years and resulted in his PhD on Sentiment Analysis. The core of his work was the creation of so-called contextualized sentiment lexicons, which yield a significant improvement over traditional sentiment lexicons thanks to their increased understanding of subtle semantic nuances.
- Organizer of the 2nd Workshop on Practice and Theory of Opinion Mining and Sentiment Analysis (PATHOS-2013)
- Organizer of the 1st Workshop on Practice and Theory of Opinion Mining and Sentiment Analysis (PATHOS-2012)
- Co-Chair of the Interest Group on German Sentiment Analysis
Assorted Selection of Publications
- Weichselbraun, Albert and Gindl, Stefan and Fischer, Fabian and Vakulenko, Svitlana and Scharl, Arno (2016) "Aspect-Based Extraction and Analysis of Affective Knowledge from Social Media Streams". IEEE Intelligent Systems . (In Press)
- Weichselbraun, Albert and Gindl, Stefan and Scharl, Arno (2014) "Enriching Semantic Knowledge Bases for Opinion Mining in Big Data Applications". Knowledge-Based Systems, 69. pp. 78-85.
- Weichselbraun, A., Gindl, S., Scharl, A. (2013), "Extracting and Grounding Context-Aware Sentiment Lexicons", IEEE Intelligent Systems, 28 (2), pp 39-46.
- Gindl, Stefan and Weichselbraun, Albert and Scharl, Arno (2013) "Rule-based Opinion Target and Aspect Extraction to Acquire Affective Knowledge". In: WWW Workshop on Multidisciplinary Approaches to Big Social Data Analysis (MABSDA-2013).
- Weichselbraun, Albert and Scharl, Arno and Gindl, Stefan (2016) "Extracting Opinion Targets from Environmental Web Coverage and Social Media Streams". In: 49th Hawaii International Conference on System Sciences (HICSS-2016), Kauai, USA.
- Clematide, S., Gindl, S., Klenner, M., Petrakis, S., Remus, R., Ruppenhofer, J., Waltinger U. and Wiegand, M. (2012). "MLSA ― A Multi-layered Reference Corpus for German Sentiment Analysis", Language Resources and Evaluation Conference (LREC-2012). Istanbul, Turkey.
- Scharl, A., Sabou, M., Gindl, S., Rafelsberger, W., Weichselbraun, A. (2012). “Leveraging the Wisdom of the Crowds for the Acquisition of Multilingual Language Resources“, Language Resources and Evaluation Conference (LREC-2012). Istanbul, Turkey.
- Weichselbraun, A., Gindl, S. and Scharl, A. (2011). “Using Games with a Purpose and Bootstrapping to Create Domain-Specific Sentiment Lexicons“, 20th ACM Conference on Information and Knowledge Management (CIKM-2011). Glasgow, UK: Association for Computing Machinery: 1053-1060.
- Gindl, S., Weichselbraun, A. and Scharl, A. (2010). “Cross-Domain Contextualization of Sentiment Lexicons”, 19th European Conference on Artificial Intelligence (ECAI-2010). H. Coelho et al. Lisbon, Portugal: IOS Press: 771-776.
- Title A-Z
- Title Z-A
- Newest Publication
- Oldest Publication
- Newest Modification
- Oldest Modification
"Aspect-Based Extraction and Analysis of Affective Knowledge from Social Media Streams"2017 in: IEEE Intelligent Systems. Volume: 32. Issue number: 3 Pages: 80-88
Extracting and analyzing affective knowledge from social media in a structured manner is a challenging task. Decision makers require insights into the public perception of a company's products and services, as a strategic feedback channel to guide communication campaigns, and as an early warning system to quickly react in the case of unforeseen events. The approach presented in this paper goes beyond bipolar metrics of sentiment. It combines factual and affective knowledge extracted from rich public knowledge bases to analyze emotions expressed towards specific entities (targets) in social media. We obtain common and common-sense domain knowledge from DBpedia and ConceptNet to identify potential sentiment targets. We employ affective knowledge about emotional categories available from SenticNet to assess how those targets and their aspects (e.g. specific product features) are perceived in social media. An evaluation shows the usefulness and correctness of the extracted domain knowledge, which is used in a proof-of-concept data analytics application to investigate the perception of car brands on social media in the period between September and November 2015.
Author(s): Albert Weichselbraun, Stefan Gindl, Fabian Fischer, Svitlana Vakulenko, Arno Scharl
Publication date: 5. 2017
Issue number: 3
Electronic version(s), related files and links: http://dx.doi.org/10.1109/MIS.2017.57
"Enriching semantic knowledge bases for opinion mining in big data applications"2014 in: Knowledge-Based Systems. Volume: 69. Pages: 78 - 85
Abstract This paper presents a novel method for contextualizing and enriching large semantic knowledge bases for opinion mining with a focus on Web intelligence platforms and other high-throughput big data applications. The method is not only applicable to traditional sentiment lexicons, but also to more comprehensive, multi-dimensional affective resources such as SenticNet. It comprises the following steps: (i) identify ambiguous sentiment terms, (ii) provide context information extracted from a domain-specific training corpus, and (iii) ground this contextual information to structured background knowledge sources such as ConceptNet and WordNet. A quantitative evaluation shows a significant improvement when using an enriched version of SenticNet for polarity classification. Crowdsourced gold standard data in conjunction with a qualitative evaluation sheds light on the strengths and weaknesses of the concept grounding, and on the quality of the enrichment process.
Author(s): Albert Weichselbraun, Stefan Gindl, Arno Scharl
Publication date: 10. 2014
Pages: 78 - 85
Electronic version(s), related files and links: http://dx.doi.org/10.1016/j.knosys.2014.04.039
"Extracting and Grounding Contextualized Sentiment Lexicons"2013 in: IEEE Intelligent Systems. Volume: 28. Issue number: 2 Pages: 39-46
A context-aware approach based on machine learning and lexical analysis identifies ambiguous terms and stores them in contextualized sentiment lexicons, which ground the terms to concepts corresponding to their polarity.
Author(s): Albert Weichselbraun, Stefan Gindl, Arno Scharl
Publication date: 27. 6. 2013
Issue number: 2
Electronic version(s), related files and links: http://dx.doi.org/10.1109/MIS.2013.41
"Incremental and Scalable Computation of Dynamic Topography Information Landscapes"2012 in: Journal of Multimedia Processing and Technologies . Volume: 3. Issue number: 1 Pages: 49-65
Dynamic topography information landscapes are capable of visualizing longitudinal changes in large document repositories. Resembling tectonic processes in the natural world, dynamic rendering reflects both long-term trends and short-term fluctuations in such repositories. To visualize the rise and decay of topics, the mapping algorithm elevates and lowers related sets of concentric contour lines. Acknowledging the growing number of documents to be processed by state-of-the-art Web intelligence applications, we present a scalable, incremental approach for generating such landscapes. The processing pipeline includes a number of sequential tasks, from crawling, filtering and pre-processing Web content to projecting, labeling and rendering the aggregated information. Processing steps central to incremental processing are found in the projection stage which consists of document clustering, cluster force-directed placement, and fast document positioning. We introduce two different positioning methods and compare them in an incremental setting using two different quality measures. The evaluation is performed on a set of approximately 5000 documents taken from the environmental blog sample of the Media Watch on Climate Change (www.ecoresearch.net/climate), a Web content aggregator about climate change and related environmental issues that serves static versions of the information landscapes presented in this paper as part of a multiple coordinated view representation.
Author(s): K.A.A. Syed, Mark Kröll, Vedran Sabol, Stefan Gindl, Arno Scharl
Publication date: 9. 2012
Issue number: 1
Simon Clematide, Stefan Gindl, Manfred Klenner, Stefanos Petrakis, R. Remus, J. Ruppenhofer, U. Waltinger, M. Wiegand"MLSA – A Multi-layered Reference Corpus for German Sentiment Analysis"2012 Pages: 3551-3556
In this paper, we describe MLSA, a publicly available multi-layered reference corpus for German-language sentiment analysis. The construction of the corpus is based on the manual annotation of 270 German-language sentences considering three different layers of granularity. The sentence-layer annotation, as the most coarse-grained annotation, focuses on aspects of objectivity, subjectivity and the overall polarity of the respective sentences. Layer 2 is concerned with polarity on the word- and phrase-level, annotating both subjective and factual language. The annotations on Layer 3 focus on the expression-level, denoting frames of private states such as objective and direct speech events. These three layers and their respective annotations are intended to be fully independent of each other. At the same time, exploring for and discovering interactions that may exist between different layers should also be possible. The reliability of the respective annotations was assessed using the average pairwise agreement and Fleiss’ multi-rater measures. We believe that MLSA is a beneficial resource for sentiment analysis research, algorithms and applications that focus on the German language.
Author(s): Simon Clematide, Stefan Gindl, Manfred Klenner, Stefanos Petrakis, R. Remus, J. Ruppenhofer, U. Waltinger, M. Wiegand
Publication date: 9. 2012
Load more results