The problem to be addressed is the reduction of attractive spaces in local commercial districts. On the other hand, shopping malls, especially large-scale ones, grow in number. Our purpose is to drive knowledge about the characteristics of attractive spaces in each of local commercial districts and shopping malls. We compare local commercial districts and shopping malls with regard to shoppers’ behavior, performing a questionnaire survey in three areas: Iwatsuki, Urawa-Misono, and Omiya. Using the machine learning method, random forests, the collected data are analyzed to clarify the characteristics of each area. The results of our analysis are as follows. People tend to go shopping at the local commercial district (Iwatsuki) individually, while people do at the shopping mall (Urawa-Misono) with their families. There are some differences between the local commercial district and the shopping mall regarding shoppers’ communication, and the downtown (Omiya) has intermediate characteristics between them.

View full abstract

The search for research seeds must be carried out using broad terms, because the query is not always initially clear; a hopeful research seed is hidden among various sets of information that has been searched for. We propose a method of investigation using exploratory filtering. First, we search for Chemical Abstracts using the name of a disease. Consequently, a great deal of obtained document sets is filtered using a dictionary of known information. After filtering, the remaining information is arranged in a list of research seeds pertaining to pharmaceuticals. We searched for literature using the search tag “breast cancer”, and filtered out the normal targets for the specific search. Subsequently, we obtained a list of novel action mechanisms. The exploratory filtering proposed in this paper is useful for finding research seeds from within hundreds of documents. We believe an investigation of research seeds has been improved using the proposed methodology.

View full abstract

Searching for information within a database using a wide range of search terms usually leads to an excess of search results. We propose a method of information seeking that uses exploratory filtering instead. Document information retrieval was conducted to support the planning of the new research theme. The obtained document sets were filtered using a dictionary of known information. After filtering, the remaining information was arranged in a list of infrequent search results. For example, literature was searched for using a disease name, and the normal targets of a specific search were filtered out. Subsequently, a list of novel action mechanisms was obtained. We propose a method of semiautomatic filtering using PubMed API by removing the general language and synonym detection. It is important to be able to extract infrequent but significant details from a surfeit of information.

View full abstract