Sales Strategy Mining Support with Visualization of Moving History

Strategic usage in data mining of sales data has come under increased focus as a result of the growth of data mining studies using electrical data, such as Point of Sale (POS) data. However, many of these mining systems only output results such as frequently appearing patterns, while, instead, they should be aimed at people who mine data. In this paper, a framework for leading and supporting new ideas from data is introduced. Based on this framework, a system that supports strategic usage in the data mining of sales data is proposed. The system deals not only with POS data, but also with the moving history of each customer. The system visualizes POS and moving history data, so that an analyzer inputs conditions to narrow down customers and acquires customer features. In addition to the ordinal outputs of a mining system, the analyzer interprets the meaning of his/her input and output to create a new strategy based on the framework. According to the experimental results, new strategies derived from the moving history were created.     

An Interactive Independent Topic Analysis for a Mass Document Review Service

In this paper, we propose an interactive constrained independent topic analysis in text data mining. Independent topic analysis (ITA) is a method for extracting independent topics from document data using independent component analysis. In this independent topic analysis, the most independent topics between each topic are extracted. By extracting the independent topic, managing documents with a large number of text data is easy with document access support systems and document management systems. However, the topics extracted by ITA are often different from the topics a user requests. For the system to be of service to users, an interactive system that reflects the user’s requests is necessary. Thus, we propose an interactive ITA that works for the user. For example, if there are three topics, i.e., topic A, topic B, and topic C, and a user choose the content from topics A and B, a user can merge those topics into one topic D. In addition, if a user wants to analyze topic A in more detail, a user could separate topic A into topics E and topic F. To that end, we define Merge Link constraints and Separate Link constraints as user requests. The Merge Link constraint is a constraint that merges two topics into one topic. The Separate Link constraint is a constraint that separates two topics from one topic. In this paper, we propose a method for extracting a highly independent topic that meets these constraints. We conducted evaluation experiments on our proposed methods, and obtained results to show the effectiveness of our approach.     

Simulation Analysis of a Dynamic Reallocation-based Routing Functionality for SAGE Application

A large amount of scientific data is generated through computation and analysis. Also, today’s scientific research necessitates an aggregation of diverse expertise from experts with different backgrounds. Therefore, visualizing and sharing these data among scientists in an intuitive and easy manner is of more importance in scientific collaborative research than ever. We have focused on SAGE, a middleware that realizes a large-scale remote visualization leveraging network streaming technique as a promising building block technology. However, no advanced network control function for efficient use of the network is equipped with SAGE although SAGE relies on a network streaming techniques. Our previous research integrated a functionality that detected network failures avoided such failure by rerouting network flows of SAGE into the functionality. Nonetheless, a network congestion avoidance functionality to adapt a collection of network flows generated by SAGE to the underlying network has not been developed yet. In this paper we explore the feasibility of a reallocation-based dynamic routing functionality for SAGE, with which all network flows on the network are rearranged. For feasibility research, we perform simulation experiments to observe the behavior of the functionality. The evaluation confirms that our proposed functionality works correctly and brings better throughput for each flow.     

Social Network Rebuilder: A Tool to Estimate a Social Network of Financial Crisis Propagation

The objective of this paper is to find a new method to estimate real social networks based on observed data collected by questionnaire surveys. Studies on social networks have been increasing in order to analyze social phenomena from a micro viewpoint. Most social phenomena can be explained by micro-level interactions among people. Spread of rumor and pandemics are typical example of micro interaction? However, there has not been much work on an analysis of real social networks based on observed data. This study tries to establish a methodology that exploits a genetic algorithm to rebuild a social network based on the data observed indirectly from real social networks. This paper introduces our proposed method, which allows us to rebuild a social network to some extent from degree distributions of a target real social network.     

Bookmarks Recommendation in Bibsonomy using Community Detection

Several academic social networks have emerged to help researchers who need to search for documents relevant to their interests. The recommendation has been adopted in many websites to suggest relevant documents to users according to their profiles. However, many academic social networks and digital libraries still lack recommendations. In this paper, we propose a new document recommendation approach for the academic social bookmarking website: Bibsonomy. In our method, we use a community detection technique to identify related users. Then, for each target user, the recommended documents are selected from their learning communities. Experimental results show that the proposed method performs better than state-of-the-art recommendation methods.     

An Algorithm of Recommending Apposite ID Photos

This article proposes an algorithm to recommend apposite ID photos for users by judging the photo of which the facial expression is apposite or not as the ID photo. Microsoft’s Kinect sensor is used for taking photos. Parts of the face, such as eyes, nose, and mouth, are analyzed as explanatory variables for judging face expression. Some body coordinate information such as head and shoulders is used to trim the photos. Neural networks and support vector machines are employed and compared to our proposed method. To achieve accurate results, ten examinees including specialized staff are selected for taking ID photo used for training models. A series of experiments are conducted to examine the validity. As a result, the accuracy of neural networks is better than that of the support vector machine. Furthermore, we analyze and discuss the difference between system results and specialized staffs’ opinions.

     

An Exploratory Look at Supply Chains in Japan from Multiscale Network Perspectives

In social network analysis, advances in social networking and computing techniques have increasingly become a popular approach for extracting features and rules of real-world networks. The network language—\(G=\{V, E \}\) provides a common representation of various networks, where G, V, and E denote the system, components, and interactions, respectively. In this study, we employ this emerging technique to discuss supply chains in Japan. We construct the supply network (i.e., system) based on the firms (i.e., components) and their transactional relationships (i.e., interactions). In comparison with the traditional approaches of industrial sectors and regional clusters, this study represents an exploratory look at supply networks, and investigates different scales of supply networks from three perspectives. (1) In the macro-scale perspective, we evaluate the “small-world” separation of supply networks using average path length. (2) In the meso-scale perspective, we detect communities of the supply networks, which can be marked for cross-location and cross-industry features. (3) In the micro-scale perspective, we investigate the “scale-free” nature of supply networks and each community using node degree-prior connections, which can find “hub” firms and simultaneously estimate the robustness of supply networks using a sequential elimination choice strategy of these hubs.     

Research Note: A Cooperative Discussion Support System through Visualization of Participants' Contributions to a Discussion

This paper proposes a new discussion support system. The proposed system supports participants in cooperative discussions, evaluates the contributions of participants to a discussion, and visualizes the contribution points in a ranking list. We have developed the proposed system and evaluated it in an evaluation experiment. Experimental results show that the proposed system supports cooperative discussions.     

Designing an Interactive Visualization to Explore Eye-movement Data

For many user applications large data sets may be collected passively and unobtrusively in the flow of their activity, and on scales ranging from the individual to increasingly larger communities. Large data sets, however, bring a concomitant need for tools to help understand what the data indicates. With the emergence of smart eyewear and the availability of sophisticated but affordable eye-tracking devices, eye movement data becomes a source of detailed information about a user’s focus and indirectly about their cognition and attention. Visualizing this usefully in terms meaningful for diagnosis however, remains a challenge. In this paper we report a new data representation from significant data sets generated by a gaze-controlled digital reading application for second language speakers. Current tools provide data sets aimed primarily towards statistical analysis of patterns: our focus is on end-user exploration of data sets in domain terms, so that practical implications can be readily identified. The visualization of horizontal eye movement data allows rapid diagnosis of problem areas in texts, informing educators immediately of individual or wider issues. The general applicability of this visualization to other applications is discussed.     

Agent-based simulation approach for disaster rescue using active RFID

After the 2004 earthquake in Japan’sNiigata Prefecture, there were many difficulties finding the victims. The earthquake caused a wired network disconnection. In addition, fixed-phone and cell-phone service systems crashed due to the rapid increase in the volume of communications. The systems’ collapse was due to the large number of users who were worried about the safety of their relatives. The same situation happened during Hurricane Katrina in the USA. Reflecting on these situations, the Japanese Ministry of Internal Affairs and Communications is trying to adopt several methods to correct these communications problems. Although these methods have not been disclosed precisely yet, we think that a predominant goal of one of the methods is most likely to find victims using RFIDs (Radio Frequency Identification) with computer sensors. To do this, the RFID method would have to be incorporated in the following ways: 1) by scattering sensor devices from helicopters when a large-scale disaster such as an earthquake occurs, 2) by making RFIDs self-organized into a network, and 3) by making the self-organized network pinpoint the position of victims. A certain amount of field-testing may be necessary to confirm the effects of this plan. However, such testing requires a great amount of time and high costs. Therefore, we adopt an agent-based simulation for such a test. In this paper, we pay specific attention to a simple and assured algorithm for discovering victims using RFIDs. First, we explain our method to confirm the location of victims. Second, we explain our method for pinpointing the position of victims using trilateration. Finally, we present our simulation results.     

Implementation issues in a grid-based multi-agent simulation system used for increasing labor supply

This paper describes issues of implementation for a Grid-based multi-agent simulation used to support decision-makers in making their decisions. Recently, social scientists including sociologists, economists, and social psychologists, have become interested in large- scale multi-agent simulation. However, users who are not familiar with operating large-scale computing resources may have a difficult time implementing these simulations. Therefore, the authors have developed a computing environment with a task-control support framework for a day care center allocation problem. In addition, we show how to implement the Grid-based multi-agent simulation system. In this paper, we examine the effectiveness of the proposed system using experiments with human subjects. By using the proposed prototype system, decision-makers were able to find near optimal solutions without examining all possible tasks.     

A Practical Teacher–Robot Collaboration Lesson Application Based on PRINTEPS

To support elementary school teachers in teaching by encouraging active learning while maintaining the interest of pupils, this study focuses on supporting teaching, learning, and monitoring the progress of students through a Teacher–Robot collaboration lesson application using not only laptops and tablets, but also robots and sensors. Since developing a lesson application is time consuming for teachers, we have developed an integrated intelligent application development platform named PRactical INTElligent aPplicationS (PRINTEPS) to aid Teacher–Robot collaboration. However, several functions and interfaces for education are missing. Therefore, in this study, we extend several functions for education to PRINTEPS. In addition, since it is necessary in learning and monitoring the progress of students to present learning content suitable to each pupil’s level of understanding, we also have provided support through the use of a tablet quiz system based on ontologies and rule bases. In the case study, we developed a Teacher–Robot collaboration lesson application and conducted lessons for sixth-grade pupils at an elementary school. From the case study, we have confirmed the effectiveness of our platform and the application.     

Mining History of Gamification Towards Finding Expertise in Question and Answering Communities: Experience and Practice with Stack Exchange

Recently, an online Q&A tool has become an essential part of individual communities and organizations of experts on specific topics. Using the answers to questions about specific topics will help such communities work more efficiently in their fields. Currently, Q&A online communities are adopting gamification to engage users by granting awards to successful users. In this paper, we investigate how to mine award achievement histories to find expertise. We propose the use of sequence analysis and clustering techniques. Specifically, we study the history of Stack Exchange, a large Q&A community that employs gamification. To the best of our knowledge, this is the first study of using award achievement history to find expertise in Q&A communities.     

Broadband Demand Analysis for Network Building

An increase of broadband demand is forecasted by transitional methods that consider the effect of this increase through many factors, such as customer requirement diversification, and new service introduction and deployment under competition. Broadband demand forecasting has become important for closing the digital divide, promoting regional developments, and constructing networks economically; therefore, a demand forecast model that considers the mechanisms of market structure is necessary. In this paper, a demand analysis method for broadband access combining macro- and micro-data mining is proposed, and the service choice behaviour of customers is introduced as a customer model not only to express the macro trend of market structure, but also to consider area marketing. The proposed method can estimate the potential demand, determine the point at which broadband demand growth peaks in a specified area, and support a decision for ultra high-speed broadband access facility installation.     

Data Mining Approach for Direct Marketing of Banking Products with Profit/Cost Analysis

Nowadays, many businesses, such as banks, use direct marketing methods to reach customers to minimize the campaigning cost and maximize the return rate. To achieve this, huge customer data should be analyzed to determine the most appropriate product offer for each customer and the most effective channel to reach her/him. However, since only a very small amount of responses collected from the customers are positive to the offers, the dataset is very imbalanced. This decreases sensitivity ratio of prediction results and makes it difficult to make a successful product and channel selection for the offer. In this paper, we propose a hybrid system, which first classifies the customers to decide if s/he is interested in the offered product, and then clusters them for product and channel suggestions. Experiments with real life banking data show very promising accuracy results for predicting the proper product and channel for the customers. Moreover, cost-profit analysis is also added to this problem. Our experiment results show that the proposed method decreases a fraction of the total profit, but since the decrease in the total cost is very large, there is a huge increase in the overall profit/cost ratio.     

Who Works at the Interface in Knowledge Spillover Across Organizational Boundaries?

To investigate the characteristics of engineers who act as an interface in transferring knowledge across national boundaries, I conducted an empirical analysis regarding the mobility of engineers in electrical manufacturing firms from Japan to South Korea. Statistical findings from negative binomial regressions show that the experience of working with foreign engineers facilitates knowledge spillover. In addition, the results show that interfirm knowledge transfer is more likely to occur when the engineers of the hiring firm work together with mobile engineers who (1) were focal members at their previous firm, (2) had a good connection with focal members, and (3) are young. This study suggests that engineers from external organizations are effective in knowledge transfer, especially if they are young, mobile engineers who were focal members at their previous firm and had a good connection with a focal member—and can act as an interface in transferring tacit knowledge.     

Comments’ Extraction by User ID,Keywords, and Anchor Texts from the Thread of a Bulletin Board System

Bulletin Board Systems (BBSs) on the Web are used by many users posting comments on threads. Each thread carries a subject of discussion. Most users post comments related to a subject. However, unrelated comments are also posted. The unrelated comments distract users and diminish their understanding of the entire story of a thread. Comments unrelated to a subject have to be filtered automatically. This paper proposes a method that extracts comments related to a thread subject from a thread of BBS. The method extracts two types of comments: comments related to a thread subject (main comments), and comments related to main comments (sub-comments). The main comments are extracted by a user ID and keywords in the comments. The sub-comments are extracted by explicit and implicit anchor texts in the comments. We experimented with the proposed method and verified that comments extracted by the proposed method support participants in understanding the entire story of a thread.     

Integrating Smart Glasses with Question-Answering Module in Assistant Work Environment

Recently, smart glasses have been applied in the field of maintenance, with which a worker goes well during work by contacting a support operator from a remote location. The worker, however, cannot go well if the support operator is not there. To solve the issues, this paper discusses how a work system should be developed by integrating smart glasses with a question-answering module. We design the work knowledge acquired from skilled people and manuals as a workflow for when type of question, rule base for how, goal tree for why, domain ontologies, and its RDF data for what. Workers can receive answers from the question-answering module incorporated with multiple knowledge bases for four types of question. The authors conducted a demonstration experiment and found that workers could perform the work more autonomously by importing the system.     

Facebook Content Strategies and Citizens’ Online Engagement: The Case of Greek Local Governments

This paper analyzes the communication strategies used by Greek local governments through the utilization of Web 2.0 technologies, specifically Facebook, and the effectiveness of these strategies in relation to citizens’ online engagement. More specifically, it examines Facebook communication strategies and levels of citizens’ engagement. For this purpose, we conducted a content analysis on the active and official Facebook pages of local municipalities in Greece from January 2017 until the end of September 2017. Our results suggest a rise in the percentage of active Facebook pages maintained by local governments in comparison to our 2014 study. Our results also show that local governments in Greece are using Facebook in a predominantly top-down manner to promote events organized by the municipality and to push one-way information to citizens about their services and actions. Local authorities have, however, made significant progress in relation to posts that support transparency and accountability and that enhance or mobilize citizens’ participation. Our evaluation of local government Facebook strategies indicates that marketing the municipality to external public, such as tourists, and providing information about services are effective strategies that drive citizens’ online attitude expression (liking), engagement (commenting), and advocacy behavior (sharing). According to our analysis, local governments in Greece prefer the strategies that we found to be the least engaging. In addition, our study provides interesting details of how specific characteristics and modes of Facebook messages (photos, videos, URLs, hashtags, and mentions) impact on citizens’ engagement. Finally, our results provide valuable insights for social media managers in local government who aim to increase the impact of their municipal Facebook pages.     

The Boosting Effect of E-WOM on Macro-level Consumption: A Cross-Industry Empirical Analysis in Japan

In this study, we carry out an empirical analysis on how electronic word-of-mouth (hereinafter “e-WOM”) marketing on e-WOM websites and electronic-commerce websites on the Internet boosts consumption on a macro-level. In our analysis, we conduct a model analysis of consumer behavior using data composed of more than 30,000 questionnaire surveys and quantitatively find the elasticity coefficient of the boost to consumption by performing a two-step GMM (generalized method of moments), which uses instrumental variables. The results of the analysis show e-WOM significantly increased expenditures in six fields: computers, electrical appliances, etc.; music; hobbies; clothing, accessories, etc.; beauty products, etc.; and goods for everyday life, etc. Furthermore, there was no field that had a significantly negative value. These results showed that, in the majority of the target fields, e-WOM had not only the effect of winning customers from the competition, but also the effect of boosting consumption on a macro-level. In addition, even from people’s subjective evaluations, there were many in all the generational groups who said that e-WOM boosted expenditures.