Yu Ichifuji

Tweets That Matter: Evidence From a Randomized Field Experiment in Japan

Although election campaigns are increasingly utilizing social media, only a few studies have investigated their effects experimentally. To fill this gap in the literature, we conducted a field experiment to examine the effects of a campaign that used Twitter during the 2013 House of Councillors election in Japan. The treatment was exposure to tweets from Tōru Hashimoto, the mayor of Osaka and co-leader of the Japan Restoration Party, who has the largest number of Twitter followers among Japanese politicians. Participants assigned to the treatment group followed Hashimoto and the two placebos, whereas those assigned to the control condition followed only the two placebos. They followed the politicians continuously for approximately one month. Pre- and posttreatment measures were collected using online surveys, and treatment compliance was continuously checked via Twitter application programming interface (API). Following Hashimoto on Twitter during the election campaign had a positive impact on feelings toward Hashimoto. This effect was not mediated by issue knowledge or the evaluation of Hashimoto’s personal traits, and no effects were observed on voting. These findings suggest that repeated exposure to a politician’s messages on Twitter may only result in a mere exposure effect, which nevertheless generates favorable overall attitudes about the politician.

Relationship between Willingness to Share Photos and Preferred Level of Photo Blurring for Privacy Protection

While expectations of personal information and life-log accumulation and utilization have been rapidly growing for more personalized services, negative issues have been increasingly recognized due to leakage of privacy information. This study aims to investigate the relationship between willingness to sharing photo and preferred level of photo blurring for privacy protection. We conducted an online questionnaire survey and analyzed it to clarify the relationship between willingness to share photos and preferred level of photo blurring by PSM (Price Sensitivity Measurement). As a result, the PSM approached enabled us to find the acceptable threshold level of photo retouching to blur identifiable people that is acceptable to users.

A New Multiple Label Propagation Algorithm for Linked Open Data

In recent years, Linked Open Data (LOD) has been attracting attention in the world since the LOD have features such as semantic web and ontology. Also, applications using the LOD have been increasing year after year in Japan and in all over the world. However, there are a problem that most of existing LOD are not linked with other LOD. Therefore, original features of the LOD have been lost. In this study, we propose a new Multiple Label Propagation algorithm for linking each other the existing LOD to bring out the original features by semi-supervised learning. This algorithm predicts semantic labels of individual data of the LOD using an assumption that adjacent nodes belong to a same or similar class. Therefore, the algorithm has new formula to consider semantic distance. Thereby, the algorithm is possible to extend links between neighborhood nodes (data). In addition, the algorithm is possible to correspond multi-label data. The results of experiments showed that the algorithm can give the label prediction values representing semantic distances, and can be processed much faster than a conventional algorithm.

Visualization of Recovery Situation in Disaster Area by Using Web Reservation Data

Public policy should be decided quickly on the basis of scientific data. However, in urgent situations, e.g., disaster recovery, it takes too long to administer a social survey and collect the results. We have therefore developed a social data collection technique that utilizes the Web reservation data of hotels and bullet trains and propose using this technique to support policymaking in real time. One challenge with using Web data is the difficulty of grasping the real situation due to problems with duplication, so we came up with a method of integrating Web reservation data. We built a social data collection infrastructure using Web data and then compared the integrated data with social survey data of Kyoto and Sendai. Results showed that the integrated data fit the social survey data within 10%. Using these data can show the resilience of hotels and shinkansen. By performing analysis on the basis of this collected data, we can support more timely policymaking. This infrastructure is effective both normal situation and disaster situation.

Tourism Local Community System Using LOD

This paper presents a new tourism local community system based on the LOD (Linked Open Data). In this study, the tourism-related data are converted into the RDF (Resource Description Framework) data and stored as LOD database in the local community system. N-triple data are generated by parsing the texts and connected to other related terms. Therefore, the relationship could be realized close to the ontology. The prototype system is constructed and the validity of the proposed system is confirmed by the experiments.

Impacts of Tourist Accommodations as Temporal Shelter on Evacuee Overflow for the Reassignment of Shelters Jurisdiction

Effective measures against natural disasters are needed worldwide, and the jurisdiction assignment of evacuation shelters during natural disasters is one such measure. In this paper, we discuss two evacuation cases involving tourist accommodations as temporary shelters. One involves evacuation to the closest shelter, and the other involves using our previously proposed optimization method for assigning jurisdiction for shelters. The impact of tourist accommodations on evacuee overflow for each case was investigated. We also explain that tourist accommodations as temporary shelter reduce the evacuee overflow at shelters by using a numerical example. We argue that its impact is limited by giving an example of a city in Japan where the evacuation and residential areas are widely spaced.

A Social Network Analysis Based on Linear Programming-Shapley Value Approach for Information Mapping

The concept of network has different meanings in different disciplines. Consider, for instance, social sciences where, mostly, denotes a set of actors or other fields defining the concept as agents, or nodes, or points, or vertices that may have relationships with one another. One of the issues to solve in social network analysis is the problem of ranking the nodes. In this paper, we combine cooperative game theory framework and linear programming techniques and suggest an equivalent alternative model to Shapley value. We present a numerical illustration explaining how our model can be applied in problems related to social networks.