Masumi Inaba

Ontology-based WOM extraction service from weblogs

In this paper, we introduce a web-based service that extracts reputations of a product from the internet. If a user inputs the product name, the service first collects articles reviewing the product from weblogs, bbs, and so on. Also, it analyzes their contents using metadata and ontologies with conventional NLP techniques. Then, it indicates the reputations (positive or negative) from the overall and several pre-defined aspects, and other related products that are the subject of much discussion in the articles. This paper illustrates two technical points regarding use of metadata and ontologies with NLP, and summarizes evaluations in a case that we applied it to a market research for a vehicle.

Ubiquitous metadata scouter – ontology brings blogs outside

In this paper, we introduce a service where ontology summarizes blogs to get useful in the real stores In ubiquitous computing environment, it would be desired for users to bind their real world situation and useful information on the Internet However, the current typical device for ubiquitous computing like a cellular phone has a small display, limited operations, and narrow-band network Therefore, semantics use to extract only the necessary information and services is for the ubiquitous computing Ubiquitous Metadata Scouter is for the user to scan products barcodes by cameras of cellular phones It gets the corresponding metadata to the product from the Internet, and collect the related blogs Then, it analyzes the contents of each blog referring ontologies, and indicates the total reputation Also, it shows other related products which are much talked about This paper illustrates each function of this service and our public experiment at the real consumer electronics store and book store in Tokyo since March 2006 It would provide an instant benefit as a semantics usecase in the ubiquitous computing.

TV navigation agent for measuring semantic similarity between programs

This paper proposes a method of computing semantic similarity which improves accuracy compared to the exisitng approaches. Most of the exisitng approaches uses WordNet as the ontology to calcualte and evaluate the similariy. A method using lightweight ontologies is proposed. The proposed method which considers offset value depends on ontologys hierarchy layer and keywords importance increases the accuracy of the correlation between computed similarities and human judgements.The method was used in a TV navigation agent system. This system introduces similar TV programs in which the user is interested. Several lightweight ontologies for TV programs to compute semantic similarity between TV programs was also developed. An experiment to evaluate the accuacy was also conducted.

Pattern-based semantic tagging for ontology population

Ontology population has emerged as an increasingly importantproblem in semantic web services. In this paper, we propose a method usingnamed entity recognition that extracts keywords from Web pages in order topopulate a product ontology. The semantic classification determines meaningsof terms and phrases by heuristic rules after the morphological analysis. Inaddition, our method classifies vocabularies into different semantic tags. Firstly,it records several lists of semantic tags to a history database. Then, we definesome rules from the lists to extract a product name. Finally, the rules build andrefine the product ontology semi-automatically. According to an evaluation,proposed method achieved 87.1% precision and 87.4% recall. Thus, it cansuggest some instances, and it decreases cost of updating the ontology.