Overview
Topic status: We're looking for students to study this topic.
Everyday a large amount of text is contributed to the World Wide Web via social media, like Tweeters, Facebook, and Blogs. People share their life online with anonymous and express their personal feelings, opinions, and comments about anything they are concerned of. From such information, current affairs may be extracted and public opinions may be extracted. For governments, a large amount of financial cost may be saved by online survey for public opinions; for news media, important events may be detected at early stage; for fashion industry, user tastes (especially for Generation Y) may be studied at maximum coverage and be captured at most accuracy; for commercial corporate, user comments may be collected efficiently so that advertisements can be put on more effectively. For all these, understanding the content of social media text is essential. However, the text of social media is usually short and contains limited information; informal or oral language is usually used in it and makes the interpretation difficult. Because of these problems, traditional text analysis techniques cannot work well, and an alternative methodology is in urgent need for modern social media analysis. This proposed Honours project aims at performing a study of social media text for its features, properties, and characteristics, and developing a preliminary theoretical model for how to discover user opinions from social media text. The research outcome of this project will make a solid, fundamental basis for sentiment analysis and opinion mining on social media, and have potential contributions to smart use of Web information. The project also has potential to extend to a broader, deeper research work of PhD project.
Hardworking, self-motivated, capable of working under stress, and willing to take challenges candidates from Information Technology, Information Sciences, and Computer Science background with distinction academic results and/or research experience are expected to join us in this project. Any enquiries are welcome. This research is partially supported by an ARC Discovery Grant from Australian Research Council (Project ID: DP0988007). The candidate will be awarded a top up scholarship based on the candidate's Academic Record.
- Study level
- Honours
- Supervisors
- QUT
- Organisational unit
Science and Engineering Faculty
- Research area
- Contact
-
Please contact the supervisor.
Professor Yuefeng Li
