• well argued and presented topic and corpus selection for the sentiment analysis
• convincing methodology for dictionary creation
• convincing sentiment analysis
• convncing evaluation and prediction power of the project (The highest grade may be obtained even if the results are not convincing but as long as the analysis of weaknesses is well founded).
• References to literature are required

The course introduces computational methods for descriptive and predictive sentiment analysis of news and business text. Students will work on their own devices (pc or mac with Java) and will use RockSteady (see e.g. http://www.electoralnetwork.org/docs/electoral-affairs-jun-2014/Social-Media-Analysis-for-Elections-SAS.pdf) for implementation. The structure of the course will be centered around the following elements with a focus on “hands-on”:

1. Text repositories - Which sources will serve my purpose?
   News bites, newspaper articles, financial reports, stock reports, social media – rss feeds, real-time scraping/harvesting vs use of established corpora.
2. Terminologies and ontologies – determining key terms and concepts in the domain of interest, keeping trace of them and using them for filtering purposes.
3. Sentiment words – How do you read sentiment, attitudes and values in a text? General language (adjectives like good, bad, nous like deterioration etc.) and specialized language (specialized terminology (bullying etc.).
4. RockSteady workshop – getting to know the tool, establishing a pilot text corpus, creation of vocabulary, testing the system, presenting the results.
5. Competition group work with technical supervision by the teachers.
6. Presentation of the results of the competition and nomination of the winning group.
7. Definition of the exam project s – oral presentation of ideas and discussion in class.

Ahmad, Khurshid (ed) (2008): Sentiment Analysis: Emotion, Metaphor, Ontology and Terminology. Workshop proceedings, LREC. http://www.lrec-conf.org/proceedings/lrec2008/

Almas, Yousif; Ahmad, Khurshid (2006): LoLo: A System based on Terminology for Multilingual Extraction. Proceedings of the Workshop on Information Extraction Beyond The Document, pages 56–65, Sydney, July 2006. © 2006 Association for Computational Linguistics

Anderson, Soren T., Ryan Kellog, James M. Salle and Richard T. Curtin.(2011).Forecasting Gasoline Prices Using Consumer Surveys.American Economic Review.  Vol 101 (No.3), pp 110-114.

Antweiler, Werner., and Murray Z. Frank.(2004). Is All That Talk Just Noise? The Information Content of Internet Stock Message Boards. The Journal of Finance. Vol. 59, No. 3 (Jun., 2004) , pp. 1259-1294

Baker, Malcolm., and Jeffrey Wurgler (2006). Investor Sentiment and the Cross-Section of Stock Returns.The Journal of Finance. Vol. 61, No. 4 (Aug., 2006) , pp. 1645-1680

Bing Liu (2010). Handbook of Natural Language Processing, Second Edition, (editors: N. Indurkhya and F. J. Damerau), 2010.

Curtin, Richard T. (2012). Consumers Adapt to a New Economic Era: More Optimism with Less Achievement.Economic Outlook Conference November 15, 2012, University of Michigan, Ann Arbor, Michigan. (http://www.sca.isr.umich.edu/fetchdoc.php?docid=48865 ).

Kontopoulos, E., Berberidis, C., Dergiades, T., & Bassiliades, N. (2013). Ontology-based sentiment analysis of twitter posts. Expert Systems with Applications, 40(10), 4065-4074. doi:http://dx.doi.org/10.1016/j.eswa.2013.01.001

Montejo-Ráez, Arturo; Martínez-Cámara, Eugenio; Martín-Valdivia, M. Teresa; Urena-López, L. Alfonso (2014). Ranked WordNet graph for Sentiment Polarity Classification in Twitter. Computer Speech and Language 28 (2014) 93–107. Available at http://ac.els-cdn.com/S0885230813000284/1-s2.0-S0885230813000284-main.pdf?_tid=c2160e6a-9cb8-11e4-9a7e-00000aacb35e&acdnat=1421327989_727cf4ecff3abc9c5f511e6ae86d868a

Ruiz-Martínez, Juana María; Valencia-García, Rafael & García-Sánchez, Francisco (2012): Semantic-Based Sentiment analysis in financial news. In: García-Crespo, Angel; Gómez-Berbís, Juan Miguel; Rodríguez-González, Alejandro; Sapkota, Brahmananda; Vidal. Maria-Esther; Lacroix, Zoé; Ruckhaus,Edna; Stojanovic, Nenad; Etzion. Opher; Stojanovic, Ljiljana: Joint Proceedings of the 1st International Workshop on Finance and Economics on the Semantic Web (FEOSW 2012), 5th International Workshop on REsource Discovery (RED 2012) and 7th International Workshop on Semantic Business Process Management (SBPM 2012) in conjunction with 9th Extended Semantic Web Conference (ESWC 2012). Available at: http://ceur-ws.org/Vol-862/FEOSWp4.pdf

Shanahan, J.G., Qu, Y., & Weibe. J. (2006). (Eds.) Computing Attitude and Affect in Text: Theory and applications.Dordrecht: Springer.

Shiller, Robert. (2000). Irrational Exuberance. Princeton: Princeton University Press.

Tetlock, Paul C. (2007). Giving Content to Investor Sentiment: The Role of Media in the StockMarket.Journal of Finance. June 2007, Vol. 62 (No. 3), pp 1139-1168