11 Hits in 1.5 sec

Subsentential Sentiment on a Shoestring: A Crosslingual Analysis of Compositional Classification

Michael Haas, Yannick Versley
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
in a data-scarce setting, harnessing cross-lingual methods as well as existing general-domain lexical resources.  ...  Starting from a small sentiment treebank modeled after the Stanford Sentiment Treebank of Socher et al. (2013) , we investigate suitable methods to perform compositional sentiment classification for German  ...  For this goal, we use a new resource, the Heidelberg Sentiment Treebank (HeiST), which is a German-language counterpart to the Stanford Sentiment Treebank in the sense that it makes explicit the composition  ... 
doi:10.3115/v1/n15-1071 dblp:conf/naacl/HaasV15 fatcat:3zxjvzthvvebjm4lkefy4pn72m

SentiMerge: Combining Sentiment Lexicons in a Bayesian Framework

Guy Emerson, Thierry Declerck
2014 Proceedings of Workshop on Lexical and Grammatical Resources for Language Processing  
Many approaches to sentiment analysis rely on a lexicon that labels words with a prior polarity.  ...  We apply this algorithm to a set of four German sentiment lexicons, to produce the SentiMerge lexicon, which we make publically available.  ...  We would like to thank the authors of the all the resources mentioned in this paper for permission to use their data. We also thank the anonymous reviewers for their helpful comments.  ... 
doi:10.3115/v1/w14-5805 dblp:conf/coling/EmersonD14 fatcat:ix4dqnlrkjcydkdzynzl4drjnq

Evaluating the Morphological Compositionality of Polarity

Josef Ruppenhofer, Petra Steiner, Michael Wiegand
2017 RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning  
Unknown words are a challenge for any NLP task, including sentiment analysis.  ...  We do this on German as it has very productive processes of derivation and compounding and many German hapax words, which are likely to bear sentiment, are morphologically complex.  ...  Acknowledgments The authors were partially supported by the German Research Foundation (DFG) under grants RU 1873/2-1 and WI 4204/2-1.  ... 
doi:10.26615/978-954-452-049-6_081 dblp:conf/ranlp/RuppenhoferSW17 fatcat:3eyacnhw7jdnvabtufjkj7uibu

Onyx: A Linked Data approach to emotion representation

J. Fernando Sánchez-Rada, Carlos A. Iglesias
2016 Information Processing & Management  
This situation motivated the creation of Onyx, a semantic vocabulary of emotions with a focus on lexical resources and emotion analysis services.  ...  Unfortunately, there are few available lexical and semantic resources for emotion recognition that could foster the development of new emotion aware services and applications.  ...  entries Annotated lexical resources are the bases for analysis of emotions in text.  ... 
doi:10.1016/j.ipm.2015.03.007 fatcat:gmlfoxrsqvdt7hodad4ppvwcru

Using games with a purpose and bootstrapping to create domain-specific sentiment lexicons

Albert Weichselbraun, Stefan Gindl, Arno Scharl
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
This paper proposes a semi-automatic approach for the creation of sentiment lexicons which assigns sentiment values to sentiment terms via crowd-sourcing.  ...  Automatically created lexicons yield a performance comparable to professionally created language resources such as the General Inquirer.  ...  GermanPolarityClues [26] or the lexicon presented by Clematide and Klenner [3] are good examples of equivalent German resources.  ... 
doi:10.1145/2063576.2063729 dblp:conf/cikm/WeichselbraunGS11 fatcat:v6lomgzulvd4zbunqbzp3vjzw4

Examining Sentiment in Complex Texts. A Comparison of Different Computational Approaches

Stefan Munnes, Corinna Harsch, Marcel Knobloch, Johannes S. Vogel, Lena Hipp, Erik Schilling
2022 Frontiers in Big Data  
To take the nuanced sentiments of literature reviews into account, we worked with a metric rather than a dichotomous scale for sentiment analysis.  ...  Literature reviews constitute a challenging text corpus for computational analysis as they not only contain different text levels—for example, a summary of the work and the reviewer's appraisal—but are  ...  CH, MK, and ES created a list of books for the purposive sample. CH and MK human-coded the seeds for the word embeddings. SM and JV pre-processed the data.  ... 
doi:10.3389/fdata.2022.886362 pmid:35600329 pmcid:PMC9114298 fatcat:pelsq6gu4zhz5pg5oe3ycap4fi

Cross-Media Sentiment Analysis on German Blogs

Nina N. Zahn, Greice P. Dal Molin, Soraia R. Musse
2021 Anais do XXXIII Seminário Integrado de Software e Hardware (SEMISH 2021)   unpublished
The comparison of this article with the analysis of sentiment among the media of Brazilian blogs finds its justification for performance results in cultural differences, since, throughout this work, Brazil  ...  Due to the increase in the amount of data on the internet, it is impracticable to carry out the sentiment analysis manually, requiring automation of the process.  ...  The lexicons used for sentiment classification of test had to contain words of the German language and are described as follows: • GermanPolarityClues [Waltinger 2010 ], is a lexical resource for sentimental  ... 
doi:10.5753/semish.2021.15813 fatcat:tp4gfg6nmrh5pbzc5bmlglm5za

Analytical Methods for Interpretable Ultradense Word Embeddings [article]

Philipp Dufter, Hinrich Schütze
2019 arXiv   pre-print
Word embeddings are useful for a wide variety of tasks, but they lack interpretability.  ...  In this work, we investigate three methods for making word spaces interpretable by rotation: Densifier (Rothe et al., 2016), linear SVMs and DensRay, a new method we propose.  ...  Germanpolarityclues: A lexical resource for german sentiment analysis. In Proceed- ings of the seventh international conference on Lan- guage Resources and Evaluation.  ... 
arXiv:1904.08654v2 fatcat:q3jnzu7tvfdjnj2zf6jkhvfctq

Proceedings of the GermEval 2017 – Shared Task on Aspect-based Sentiment in Social Media Customer Feedback [article]

Michael Wojatzki, Eugen Ruppert, Torsten Zesch, Chris Biemann, DuEPublico: Duisburg-Essen Publications Online, University Of Duisburg-Essen
Sentiment Analysis is an important task to analyze customer feedback and a growing number of Shared Tasks exist for various languages.  ...  The Shared Task is a first step in sentiment analysis for this domain.For the GermEval 2017 Shared Task, we received 8 submissions. One submission was withdrawn from the proceedings.  ...  Finally, we thank the Interest Group on German Sentiment Analysis (IGGSA) for their endorsement.  ... 
doi:10.17185/duepublico/46421 fatcat:bt6bmmuorrhvtftnxh2sp6dgpa

Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments [article]

Julian Risch, Anke Stoll, Lena Wilms, Michael Wiegand
On out-of-sample data, our best ensemble achieved a macro-F1 score of 0.73 (for all subtasks), and F1 scores of 0.72, 0.70, and 0.76 for subtasks 1, 2, and 3, respectively.  ...  In this contribution, we fine-tuned German BERT and German ELECTRA models to identify toxic (subtask 1), engaging (subtask 2), and fact-claiming comments (subtask 3) in Facebook data provided by the GermEval  ...  This research also used free computing resources provided by the GraphCore Academic Program and Google Colab.  ... 
doi:10.48415/2021/fhw5-x128 fatcat:u3fcq4x23jba7ic2a5ldcsdbna

Network-oriented Customer Valuation and Social Engagement Analysis in Online Customer Networks

Georg Lindner
An online customer network thus acts as a specialised online community for customers who want to share common social and commercial interests with other customers and interact with the sponsoring company  ...  The emergence of web 2.0 technologies had major consequences for the relationship between customers and companies.  ...  Waltinger, U.: GermanPolarityClues: A Lexical Resource for German Sentiment Analysis.  ... 
doi:10.5283/epub.38180 fatcat:mrwdn5xadzfw5pj26kuzoketsa