Yukari Shirota

Once a disaster occurs, people discuss various topics in social media such as electronic bulletin boards, SNSs and video services, and their decision-making tends to be affected by discussions in social media. Under the circumstance, a mechanism to detect topics in social media has become important. This paper targets the East Japan Great Earthquake, and proposes a time series topic detection method based on modularity measure which shows the quality of a division of a network into modules or communities. Our proposed method clarifies emerging topics from social media messages by computing the modularity and analyzing them over time, and visualizes topic structures. An experimental result by actual social media data about the East Japan Great Earthquake is also shown.

In many companies of the province of Tohoku (North-East Japan), stock prices were declining just after the East-Japan earthquake. However, on the other hand, some companies' stock prices rose in Tohoku. We have analyzed the reasons using text mining technologies on web data. In our studies, a combination of a stock price analysis and the text mining of the company can weave unexpected facts like a word associative game. First we surveyed stock prices of all listed companies that were headquartered in the damaged three prefectures in Tohoku. Then, we found the remarkable growth of YAMAYA which was an alcohol wholesaler and retailer company. The headquarters are located in Sendai-city, the capital and biggest city of Miyagi prefecture. On the other hand, we found YAMAZAWA's growth which was the same kind of an alcohol retailer company as YAMAYA. Although stock prices of almost all super markets in Tohoku intensely grew just after the disaster, the growth of YAMAYA and YAMAZAWA was distinguished. Therefore we conducted text mining to seek the reason of the company's stock price increase. As a result, we thought the alcohol consumption in Sendai-city caused the rapid stock price rises. In addition, from the comparison, we found that the recovery of YAMAZAWA's was quicker than that of YAMAYA's. We think that the reason for the YAMAYA's delay is that the earthquake damage in Sendai-city was larger than that in Yamagata. YAMAWA is headquartered in Sendai-city and YAMAZAWA is headquartered in Yamagata prefecture. The difference about locations would make the delay in the stock price recoveries. From the analysis, we inferred that an increase of alcohol consumption was one of the triggers for the economic reconstruction in Sendai-city. The paper discusses the economic reconstruction processes through increases of stock prices in the Tohoku province. © 2013 IEEE.

After the East Japan Great Earthquake occurred in Japan on 11th March 2011, many messages related to the earthquake were posted to social media. Especially, in Asian countries, a lot of messages about the earthquake were posted, so that different topics such as concerning about damages by the earthquake, afflicted people were observed, etc. observed. These topics can be recognized as reactions to the earthquake. Therefore, exploring topics related to the earthquake on social media in Asian countries gains a rich insight into the Asian social context. The goal of our research is to analyze Asian people reactions to the East Japan Great Earthquake on social media using data mining technique. As the first step, this paper targets Thai language and conducts the preliminary approximation to investigate topics on Thai social media. We analyze how Thai people reacted to the earthquake and compare with reactions in Japan. © 2013 IEEE.

Social media, which enable people to easily communicate and effectively share the information through the web, are rapidly spreading recently. In such media, effective topic extraction technique from messages has been significant so that trend topics and their reputation can be recognised. However, since messages contain redundancy and topic boundaries are ambiguous, it is difficult to extract appropriate topics. As the first step for topic extraction, this paper proposes an effective measure to automatic determination of appropriate number of topics based on the intra-cluster distance and the inter-cluster distance among topic clusters. We present our experimental results to show the effectiveness of our proposed approach. Copyright © 2012 Inderscience Enterprises Ltd.

This paper presents a concept model for solving bond mathematics problems; it is the manner in which our knowledge concerning bond mathematics is organized into a cognitive architecture. We build a concept model for bond mathematics to achieve good organization and to integrate the knowledge for bond mathematics. The ultimate goal is to enable many students to understand the solution process without difficulty. Our concept model comprises entity-relationship diagrams, and using our concept models, students can integrate financial theories and mathematical formulas. This paper illustrates concept models for bond mathematics by showing concrete examples of word mathematics problems. It also describes our principles in developing the concept model and the descriptive power of our model.

This paper proposes a method to discover consumer behavior from buzz marketing sites. For example, in 2009, the super-flu virus spawned significant effects on various product marketing domains around the globe. Using text mining technology, we found a relationship between the flu pandemic and the reluctance of consumers to buy digital single-lens reflex camera. We could easily expect more air purifiers to be sold due to flu pandemic. However, the reluctance to buy digital single-lens reflex cameras because of the flu is not something we would have expected. This paper applies text mining techniques to analyze expected and unexpected consumer behavior caused by a current topic like the flu. The unforeseen relationship between a current topic and products is modeled and visualized using a directed graph that shows implicit knowledge. Consumer behavior is further analyzed based on the time series variation of directed graph structures.

We would like to make a database of the time-series economics event data issued by the East Japan earthquake disaster on March 2011 so that we could hand the data to posterity. The point of the recording is social network data mining and visualization. To emphasize the time-series data, we will add event text information by the data mining to the economic index data. Then we will conduct visualization of the multi-layered relationships among the economic events. The sophisticated graphics with a slider and three-dimensional graphics would be helpful to have young people understand what had been happened under the calamity. If we published research results as a form of technical papers, no young people would read and understand the results. Therefore, we will intend to develop teaching materials by using the economic analytical data. The point of our analytical methods is an insight into the nature of real-time process and the ignorance, which has been proposed by Prof. Okumura. To emphasize the real-time process of economic events, using the storylines, we would be able to educate economical actions of each economical entity varying from hour to hour under the calamity situations fraught with uncertainty

When the student is not able to solve a given problem, a plausible deductive reasoning process should be offered to him/her. Our final goal is a development of an e-Learning system which could help students not too much and not too little so that they can acquire as much deductive experience of independent work as possible. In the paper, we illustrate a solution plan graph which is a plausible deductive reasoning material with a concrete word problem. Our guiding principle for conducting the deduction is the thinking method of "working backwards" from the unknown. The paper also illustrates the details of the working backwards method.