Universität Wien

132034 UE Social media data: extraction and analysis (2022S)

Continuous assessment of course work
REMOTE

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

Language: English

Lecturers

Classes (iCal) - next class is marked with N

  • Tuesday 01.03. 11:30 - 13:00 Digital
  • Friday 04.03. 09:45 - 11:15 Digital
  • Tuesday 08.03. 11:30 - 13:00 Digital
  • Tuesday 15.03. 11:30 - 13:00 Digital
  • Friday 25.03. 09:45 - 11:15 Digital
  • Tuesday 29.03. 11:30 - 13:00 Digital
  • Friday 01.04. 09:45 - 11:15 Digital
  • Friday 08.04. 09:45 - 11:15 Digital
  • Tuesday 26.04. 11:30 - 13:00 Digital
  • Friday 29.04. 09:45 - 11:15 Digital
  • Friday 06.05. 09:45 - 11:15 Digital
  • Tuesday 10.05. 11:30 - 13:00 Digital
  • Friday 13.05. 09:45 - 11:15 Digital

Information

Aims, contents and method of the course

Over the past 15 years, social networks have become a very popular means of communication, sometimes surpassing more traditional means of disseminating information such as television and radio. These digital platforms are built with the intent to connect people and allow them to share news but also their opinions through comments, reactions, likes etc..
The more "horizontal" structure of social networks has therefore contributed to a greater democratization of the debate, but the decentralization that makes all users both actors and spectators, the great speed with which information is disseminated and the presence of bots have also posed major problems such as the veracity of the news, the reliability of individual users and the lack of control over phenomena such as hate speech and discrimination of various kinds.
In this context, social networks, on the other hand, offer us the unique opportunity to have at our disposal a large amount of data to analyze and understand the public debate around any topic.

This course offers the basics to make a first and simple analysis of data from social networks, focusing not only on the texts of individual posts, but also on the information coming from the structure of the data itself.
Students will learn how to download data (including metadata) from Twitter through the API offered by the platform for academic use, preprocess it, and develop simple analyses such as building a retweet network and highlighting its most influential actors or exploring the presence of communities.

Although the course will have a rather practical setting with hands-on sessions, students will still be provided with a theoretical background with some examples of recent research and publications related to these topics. The students will use R (but they are free to use Python for their project) as main programming languages and they will be offered a general introduction to it in the first lessons. Slides and R notebooks will be available after each lecture.

The course will be online and will end in May, but the teacher is available on Skype for clarifications and questions related to the course.

Assessment and permitted materials

The course uses continuous assessment and there is no final examination. Throughout the semester students develop a personal project and their progress will be evaluated through homework assignments (60% of grade) and the final submission of the project (30%).

The remaining 10% of the course grade is awarded for engagement in the course activities.

The final project could be also shared in groups of 2-3 students each, depending on how many students will attend the course. We will define this in the first lectures.

Minimum requirements and assessment criteria

Students will need to have access to a computer for the practical component of the course.

No prior knowledge is assumed, but a basic familiarity with R/Python languages or general webscraping API will help.

The course is evaluated according to a points system. You can achieve 100 points in the course. The research project is rated with up to 90 points (60 for homework assignments and 30 for final submission). Students participation will be rated with up to 10 points.

The minimum for the positive completion of the courses is 51 points.

Conversion of points to grades: 0-50 = insufficient, 51-60 = sufficient, 61-70 = satisfactory, 71-80 = good, 81-100 = very good

Examination topics

- basic R/Python exercises
- download and preprocess Twitter data
- analyse Twitter data (example: retweet/mention network analysis)

Reading list

https://developer.twitter.com/en/products/twitter-api/academic-research/application-info

Conover, Michael, et al. "Political polarization on twitter." Proceedings of the International AAAI Conference on Web and Social Media. Vol. 5. No. 1. 2011.

González-Bailón, Sandra, et al. "The dynamics of protest recruitment through an online network." Scientific reports 1.1 (2011): 1-7.

Pellert, Max, et al. "Dashboard of sentiment in Austrian social media during COVID-19." Frontiers in big Data (2020): 32.

Association in the course directory

DH-S II, S-DH (Cluster III: Theatre, Film and Media)

Last modified: Th 04.07.2024 00:13