Knowing the reputations of your own and/or competitors' products is important for marketing and customer relationship management. It is, however, very costly to collect and analyze survey data manually. This paper presents a new framework for mining product reputations on the Internet. It automatically collects people's opinions about target products from Web pages, and it uses text mining techniques to obtain the reputations of those products. On the basis of human-test samples, we generate in advance syntactic and linguistic rules to determine whether any given statement is an opinion or not, as well as whether such any opinion is positive or negative in nature. We first collect statements regarding target products using a general search engine, and then, using the rules, extract opinions

This paper proposes a novel approach to accurately searching Web pages for relevant information in problem solving by specifying a Web document category instead of the user's task. Accessing information from World Wide Web pages as an approach to problem solving has become commonplace. However, such a search is difficult with current search services, since these services only provide keyword-based search methods that are equivalent to narrowing down the target references according to domains. However, problem solving usually involves both a domain and a task. Accordingly, our approach is based on problem solving tasks. To specify a user's problem solving task, we introduce the concept of document types that directly relate to the problem solving tasks; with this approach, users can easily designate problem solving tasks. We implemented PageTypeSearch system based on our approach. Classifier of PageTypeSearch classifies Web pages into the document types by comparing their pages with typical structural characteristics of the types. We compare PageTypeSearch using the document typeindices with a conventional keyword-based search system in experiments. The average precision of the document type-based search is 88.9%, while the average precision of the keyword-based search is 31.2%. Moreover, the number of irrelevant references gathered by our system is about one-thirteenth that of traditional keyword-based search systems. Our approach has practical advantages for problem solving by introducing the viewpoint of tasks to achieve higher performance.

This paper describes a new hardware algorithm for morpheme extraction and its implementation on a specific machine (MEX-I), as the first step toward achieving natural language parsing accelerators. It also shows the machine's performance, 100--1,000 times faster than a personal computer. This machine can extract morphemes from 10,000 character Japanese text by searching an 80,000 morpheme dictionary in 1 second. It can treat multiple text streams, which are composed of character candidates, as well as one text stream. The algorithm is implemented on the machine in linear time for the number of candidates, while conventional sequential algorithms are implemented in combinational time.

The following proposal is for a Japanese sentence analysis method to be used in a Japanese book reading machine. This method is designed to allow for several candidates in case of ambiguous characters. Each sentence is analyzed to compose a data structure by defining the relationship between words and phrases. This structure ( named network structure ) involves all possible combinations of syntactically collect phrases. After network structure has been completed, heuristic rules are applied in order to determine the most probable way to arrange the phrases and thus organize the best sentence. All information about each sentence---the pronounciation of each word with its accent and the structure of phrases---will be used during speech synthesis. Experiment results reveal: 99.1% of all characters were given their correct pronunciation. Using several recognized character candidates is more efficient than only using first ranked characters as the input for sentence analysis. Also this facility increases the efficiency of the book reading machine in that it enables the user to select other ways to organize sentences.