Fake reviews/spammers detection
As reputation of a store is getting significantly important in online shopping market, companies which provide services to purposely raise a store’s reputation have emerged in crowdsourcing websites. These services are done by left fake reviews after fake transactions. How to detect the fake reviews...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/66803 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | As reputation of a store is getting significantly important in online shopping market, companies which provide services to purposely raise a store’s reputation have emerged in crowdsourcing websites. These services are done by left fake reviews after fake transactions. How to detect the fake reviews and the spammers has become a practical issue with huge commercial values. This project was to address this issue through a systematical way of data collection and developing a methodology to detect fake reviews and spammers, focusing on building the relations between reviewers and stores. The report discussed motivations of the project and the entire research processes including scoping finalization, project scheduling. The report further detailed the processes of crowdsourcing website investigation, data collection, data preprocessing, data labeling, methodology developing and evaluation. The report also included limitations for future improvements. Lastly, the project delivered a set of files which includes the details of development of the methodology. |
|---|