Infopaket

Automatic Content and Sentiment Analysis

ДВС.1.06

Вибіркова дисципліна для ОП

Second

2021/2022

3 Semester

2

PLO 11. To perform a scholarly analysis of linguistic, speech, and literary material, interpret and structure it considering expedient methodological principles, and formulate summarizations based on the individually processed data. PLO 16. To use specialized conceptual knowledge in applied linguistics to solve complex tasks and issues, which requires updates and integration of knowledge, often under conditions of incomplete/lacking information and contradictory requirements. PLO 17. To plan, organize, perform, and present the research and or innovative developments in an applied linguistics field. PLO 20.1. To apply the methods of designing dialogue systems (question-answer system), systems of speech recognition and synthesis, automatic editing and text retrieval, content analysis, and sentiment analysis in the creation of linguistic information technologies. PLO 22.1.

Full-time form

Before starting the course, students should know the main stages of automatic text analysis, and have basic factual knowledge of a linguistic nature. Be able to collect and interpret information about linguistic phenomena; single out the features of the products of speech activity necessary for the automation of text analysis, apply the organization of the language system in speech analysis; plan and evaluate own work; use interactive and multimedia tools. Have elementary skills in scientific research and information management; critical attitude to the analyzed phenomena; use of foreign language professional informative sources; production of complex oral and written messages; interaction and cooperation in learning in exploratory situations.

The purpose of the discipline is to study the history and state of development of the problem of automatic content and sentiment analysis, methods of automatic tonality analysis of texts; mastering the skills of working with existing systems, and using various assessment scales to form the necessary professional competencies of future specialists.

Nasukawa T. and Yi J. Sentiment Analysis: Capturing Favorability Using Natural Language Processing. Proceedings of the 2nd International Conference on Knowledge Capture, Florida, 23-25 October 2003, 70–77. Liu Bing. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. 2012. #5 (1). Pp. 1–167. URL: https://www.cs.uic.edu/~liub/FBS/NLP-handbook-sentiment-analysis.pdf Taboada M., Brooke J. Lexicon-based methods for sentiment analysis. Computational Linguistics. 2011. 37 (2). Pp. 272–274. URL: https://dl.acm.org/doi/10.1162/COLI_a_00049 Vryniotis V. The importance of Neutral Class in Sentiment Analysis. 2013. URL: http://blog.datumbox.com/the-importance-of-neutral-class-in-sentiment-analysis/

Lectures, practical classes, independent work.

Assessment of semester work: 1. Oral answer, practical tasks, additions, participation in lectures, and practical discussions: 40/64 points. 2. Test: 20/36 points. The overall score for the semester consists of points received for classroom work (which synthesizes and independent work on processing theoretical material for classroom preparation: oral answers, additions, and tests) and independent work. All types of work for the semester have a total of 100 points. The semester evaluation forms the intermediate control score. The points obtained by the discipline are transferred in the percentage equivalent (50% of the obtained points - from the maximum number of 100 points - 50 points) to the formation of the total score for the semester of the next part (part 5 "Automatic referencing") of the complex / multi-semester discipline "Linguistic aspects of NLP-systems".

Ukrainian, English