Masaharu Hirota

Visualizing High-Risk Paths using Geo-tagged Social Data for Disaster Mitigation

The 2011 Tohoku earthquake and tsunami showed the importance of smooth evacuation to nearby safe evacuation facilities. Smooth evacuation from crowded areas like train stations is difficult because people facing disaster often cannot find good paths to the nearest safe places and their evacuation may create congestion, which again hinders smooth evacuation. For smooth evacuation, the safety of roads used for evacuation needs to be evaluated. This evaluation requires 1) geographical characteristics of roads such as the risk of collapse of neighboring buildings and road width and 2) crowdedness of roads at the moment of disaster. While previous studies considered the former, the latter information has not been well studied because the crowdedness depends on the demographics of a city, which is quite dynamic and difficult to measure. For example, daytime and nighttime populations of a city differ greatly. This paper proposes a method that measures demographic snapshots of a city from time- and geo-stamped micro-blog posts and visualizes high-risk evacuation roads on the basis of geographical characteristics and demographics. Our method enabled visualization of high-risk evacuation roads on a per-hour basis. We also qualitatively analyze and discuss the visualization results.

Inferring Tourist Behavior and Purposes of a Twitter User

The importance of tourism information such as tourism purposes and tourist behavior continues to increase. However, obtaining precise tourist information such as the tourist destination and tourism period is difficult, as is applying that information to actual tourism marketing. We propose a method to classify Twitter user into tourist behavior and tourism purposes, extracting related information from Twitter posts. Our experiments demonstrated a 0.65 F-score for multi-class classification, showing accuracy for inferring tourist behavior and tourism purposes.

Where Is the Memorable Travel Destinations

In this paper, we propose a method to discover “memorable” travel destinations. Our hypothesis is that differences in the numbers of photographs posted to blogs for users indicate how memorable the travel destination remained to the user. We specifically examined the number of photographs posted to blogs for each user and each area. Our proposed method does not specifically examine the number of photographs simply for each place, but it examines user characteristics. We conducted experiments to demonstrate the ranking travel destinations in Japan and throughout the world using our proposed method. Results show that our method ranked not only the famous travel destinations highly but also unpopular travel destinations in terms of being memorable.

Analyzing Travel Behavior Using Multi-label Classification From Twitter

In this paper, we analyze the changes in behavior of travelers on the basis of the kind of travel and travel period using geotagged tweets. Travel can be classified into various types of purposes. For example, travelers visit Tokyo for various purposes like sightseeing or transiting to another area. In this paper, for a first experiment, we classified travelers visiting Tokyo in accordance with whether their main destination was Tokyo or not. Using the results, we discuss the differences in the behaviors of people on travels to and through Tokyo. We also used the same results to see whether the behavior of travelers changes depending on the length of travel and the day of the travel. For the second experiment, we compared the behaviors of travelers visiting Tokyo from two different regions (Kanto and Kyushu) to see whether place of residence affects behavior on travels of different lengths and on different days.

How to Find Accessible Free Wi-Fi at Tourist Spots in Japan

We propose a method of finding spots at tourist attractions that do not have accessible Free Wi-Fi by using social media data. Although it is an important issue for the government to determine where they should install Free Wi-Fi equipment, it involves a high human cost. We focused on the difference in usage of social network services (SNSs) to find where there was a lack of Free Wi-Fi. We posed two simple hypotheses: (1) uploaded photos on Flickr, where batch-time SNS reflects the popularity of attractions from the travelers’ perspective, and (2) posts on Twitter, where real-time SNS reflects the communications environment. Differences in the distributions of posts in these SNSs indicate the gap in needs and the current status of communications infrastructures. Experimental results obtained from fieldwork in the Yokohama area clarified that although our method could locate places that were popular with tourists, some of these locations did not have Free Wi-Fi equipment installed there.