Summary of the paper
| Title | Towards Sentiment Analysis of Financial Texts in Croatian |
|---|---|
| Authors | Željko Agić, Nikola Ljubešić and Marko Tadić |
| Abstract | The paper presents results of an experiment dealing with sentiment analysis ofCroatian text from the domain of finance. The goal of the experiment was todesign a system model for automatic detection of general sentiment and polarityphrases in these texts. We have assembled a document collection from websources writing on the financial market in Croatia and manually annotatedarticles from a subset of that collection for general sentiment. Additionally,we have manually annotated a number of these articles for phrases encodingpositive or negative sentiment within a text. In the paper, we provide ananalysis of the compiled resources. We show a statistically significantcorrespondence (1) between the overall market trend on the Zagreb StockExchange and the number of positively and negatively accented articles withinperiods of trend and (2) between the general sentiment of articles and thenumber of polarity phrases within those articles. We use this analysis as aninput for designing a rule-based local grammar system for automatic detectionof polarity phrases and evaluate it on held out data. The system achievesF1-scores of 0.61 (P: 0.94, R: 0.45) and 0.63 (P: 0.97, R: 0.47) on positiveand negative polarity phrases. |
| Language | Document Classification, Text categorisation |
| Topics | Emotion Recognition/Generation, Information Extraction, Information Retrieval, Document Classification, Text categorisation |
Full paper  |
Towards Sentiment Analysis of Financial Texts in Croatian |
| Bibtex | @InProceedings{AGI10.876, author = {Željko Agić, Nikola Ljubešić and Marko Tadić}, title = {Towards Sentiment Analysis of Financial Texts in Croatian}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |