Keep me posted! Human and machine learning analysis of Facebook updates
Journal Title: EAI Endorsed Transactions on e-Learning - Year 2015, Vol 2, Issue 7
Abstract
The key element of Facebook social network platform is the status updates, in which the user can upload text or other media such as pictures and videos. In this study, we manually classified more than 3500 Facebook status updates (FSUs) by the subject, the emotional activation, the medium used, the originality and the self-centeredness. We then cross-tabulated that information with demographic factors such as gender and occupation. Thirty students participated in the categorization task, each annotating more than 100 FSUs of their Facebook friends’ FSUs. Statistical and supervised machine learning analysis was then applied to the categorized features. The text itself was not analyzed further after the annotation for the purpose of preserving the privacy and anonymity of the FSU authors. Results show that FSUs vary in subject, emotional connotation and structure as a function of demographic factors like gender and occupation of the poster. Statistical analysis and supervised machine learning are able to predict the demographic and emotional expressions based on the other features annotated by the participants.
Authors and Affiliations
Franco Delogu, Marija Franetovic, Lior Shamir
Keywords
Related Articles
- EP ID EP45948
- DOI http://dx.doi.org/10.4108/icst.mobimedia.2015.259075
- Views 256
- Downloads 0
Teaching Basic Ideas in Logic Using E-learning Tools
This paper is a study of various e-learning strategies for teaching basic ideas in logic. The focus is mainly on syllogistic validity and deduction. It is a continuation of earlier studies involving practical experiments...
Is Technology Mediated Learning Really Improving Performance Of Students?
This paper examines the role of information technology in learning environments. In particular, it goes through the analysis of the impact of the use of information technology in high school students’ performance. It des...
Key Frame Extraction for Text Based Video Retrieval Using Maximally Stable Extremal Regions
This paper presents a new approach for text-based video content retrieval system. The proposed scheme consists of three main processes that are key frame extraction, text localization and keyword matching. For the key-fr...
Exploring the Value of Educational Accessibility and Learning through Virtual Worlds
Virtual worlds allow for an immersive 3D experience with rich interactive content and learning potential for students. Through this technology, educators have abundant creative power to design and facilitate meaningful l...
Web Log Pre-processing and Analysis for Generation of Learning Profiles in Adaptive E-learning.
Adaptive E-learning Systems (AESs) enhance the efficiency of online courses in education by providing personalized contents and user interfaces that changes according to learner’s requirements and usage patterns. This pa...