| CODE | LIN5507 | |||||||||
| TITLE | Social Media as Multimodal Text | |||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | |||||||||
| MQF LEVEL | 7 | |||||||||
| ECTS CREDITS | 10 | |||||||||
| DEPARTMENT | Institute of Linguistics and Language Technology | |||||||||
| DESCRIPTION | Social media have revolutionised the structure of the Worldwide Web, as well as the way users interact with it. The web can be viewed as a source of data that can be exploited by intelligent systems incorporating some kind of learning mechanism (including learning the structure and function of human language). It is also an important source of data for human analysts seeking insight into how technology-mediated communication occurs. In this respect, social media present novel and interesting challenges, insofar as the data is (a) interactive; (b) constantly evolving; (c) multimodal and (d) has specific linguistic properties, especially in relation to stylistic features such as brevity, and lexico-grammatical features associated with the medium. This unit will introduce social media and their uses in Human Language Technology, focusing on the following topics: 1. What social media are, their architectural properties and the relationship to new generations of mobile devices; 2. Social media as multimodal text resources, with particular reference to the linguistic and stylistic properties of text; 3. Sociological and socio-linguistic aspects of social media and how they impact (linguistic) interaction; 4. The use of social media for the automatic extraction of linguistic knowledge, especially (a) opinion mining and sentiment analysis; (b) temporal knowledge. Study-unit Aims: The unit will bring to bear knowledge of HLT techniques to the automatic analysis of social media. The unit will help students master techniques for making the user's social media experience more seamless, through the use of NLP technology. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Automatically extract information from brief messages by multiple users; - Design intelligent, language-sensitive systems for the analysis of user postings on social media of different kinds; - Choose the best from among a range of machine learning and extraction techniques to extract information of a particular kind. 2. Skills: By the end of the study-unit the student will be able to: - Critically analyse the role of various social media on communication and language; - Appraise the impact of contemporary web technology on society; - Use mining and learning techniques for information extraction from unstructured data; - Follow and understand new developments in social media as they appear on the scene. Main Text/s: - B. Pang and L. Lee (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval 2(1-2), pp. 1–135. [Available online at http://www.cs.cornell.edu/home/llee/opinion-mining-sentiment-analysis-survey.html] - A. Newson, D. Houghton and J. Patten (2009). Blogging and other social media. Farnham, UK: Gower. In addition to the above, various other texts will be proposed, in the form of articles reflecting the state of the art. |
|||||||||
| ADDITIONAL NOTES | Pre-requisite Study-units: Core units in HLT | |||||||||
| STUDY-UNIT TYPE | Lectures, Practicum & Project | |||||||||
| METHOD OF ASSESSMENT |
|
|||||||||
| LECTURER/S | Albert Gatt |
|||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |
||||||||||