Domain-Assisted Hierarchical Organization of Product Consumer Reviews (11397N)
IDA Technology Roadmap 2012
This technology falls in the following categories of Singapore's IDA Infocomm Technology Roadmap 2012:
For more information on this technology contact:
This invention presents a novel method to organize online product reviews into hierarchies that are the result of a combination of product specifications (i.e., domain knowledge) and consumer reviews. Information thus organized is amenable to queries by specific product features that may result in more focused insights for producers and consumers of goods.
This invention also supports implicit aspect identification, that is, implicit reference to certain aspects or features of a product.
This invention’s basic mechanism consists of four steps: 1) Initial hierarchy acquisition, 2) Aspect identification, 3) Aspect hierarchy organization, and 4) Sentiment classification.
Companies with a stake in the identification of public perception of products, market forecast and trends, and product review aggregators could benefit from the use of this technology. Consumers could also benefit from this technology as it would allow focused assessment of a product’s individual features.
Technology Readiness Level 6 on the scale by the Ministry of Defence Singapore.
About the Research Group
Professor Chua Tat-Seng is founding Dean of the School of Computing at NUS and director of the NExT Center, a joint venture between NUS and Tsinghua University with the support of MDA of Singapore. The center focuses on crawling and mining user-generated content in Singapore and China in the areas of location-oriented information, topic-oriented information, application-oriented information and structured information.