Before making a purchase, more and more consumers in recent years are consulting other consumers¡¦ product reviews online, to assist them in making a purchasing decision. However, due to the massive amount of online reviews, consumers can hardly get useful information effectively. Hence, information overload has become a problem. Query functions in search engines like Yahoo and Google can help users find some of the reviews that they need for specific information. Nevertheless, the returned pages from these search engines are still beyond the visual capacity of humans.
Therefore, this study aims to develop a new concept of personalized recommendation based on consumer product reviews to solve the afore-mentioned problem. A series of laboratory experiment examines the effectiveness of the proposed approach and compares this approach with other traditional approaches on precision of recommendation. Meanwhile, the meaning of the recommendation behind each approach is explained. Lastly, the prototype of recommendation system based on the proposed approach is illustrated. Our system can display the trend of the gathered consumer reviews in a graphical way, such as a product satisfaction run chart. The development of recommendation systems is not only beneficial to consumers, but also advantageous to sellers.
| Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0728110-012135 |
| Date | 28 July 2010 |
| Creators | Lee, Chung-Wei |
| Contributors | Wei-Po Lee, Te-Min Chang, Bing-Chiang Jeng |
| Publisher | NSYSU |
| Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
| Language | Cholon |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0728110-012135 |
| Rights | not_available, Copyright information available at source archive |
Page generated in 0.0023 seconds