| Author: | Huang, Lifeng |
| Title: | Chinese neologism discovery with statistics features in social media data |
| Advisors: | Ng, Vincent T. Y. (COMP) |
| Degree: | M.Sc. |
| Year: | 2015 |
| Subject: | Chinese language -- New words. Web usage mining. Social media. Data mining. Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Computing |
| Pages: | v, 69 leaves : illustrations ; 30 cm |
| Language: | English |
| Abstract: | Sentiment analysis has always found its practical use in collecting people’s preferences towards any subject in the context of social media. Unlike normal words available in dictionaries, neologisms are not easy to be labeled with a sentimental direction with current sentimental analysis algorithms. The first barrier to overcome is the need of a reliable neologism detection method. Our work proposes a Chinese neologism detection method based on statistical data ranking and support vector machine (SVM) classification. Statistical data includes frequency, duration of appearance and the number of users using a neologism. Seven different rankings are generated according to different statistics features and feature combinations. The rankings and their differences can be used to select candidate neologisms with the support of SVM. The SVM classifier aims to utilize a proper function f (x,y) with training data, and classify candidate words as “neologism or “neologism with the calculated function value. The experimental results show ranking and their differences are useful information in neologism discovery, and SVM classifier showed a satisfied recall rate as high as 82.22%, the best precision 94.72% and the highest F-value as 85.35%. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b27815201.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.95 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/7879