Robin M. E. Swezey

An e-Participation support system for regional communities based on linked open data, classification and clustering

In this paper, we present an e-Participation Web system for various platforms and mobile phones, based on linked open data, classification and clustering. The system aims at supporting citizen e-Participation in ongoing regional debates by gathering and openly publishing news and opinions from the Web for easy comprehension and commenting. Our study helps us define relevant evaluation criteria for an adequate citizen discussion system in the new context of open government, the Web, and mobile computing. We present the system, O2, and its application citispe@k, as well as its underlying components: ontology structure, classification and clustering. We then conduct a comparison with existing systems and find that our system is a better approach for efficient citizen e-participation when compared to current existing systems.

A Real-Time Collaborative Web Page Editing System WFE-S Based on Cloud Computing Environment

We are developing WFE, a system for Real-Time Collaborative Editing (RTCE) for existing Web pages. We aim to enable several users to perform simultaneous modifications on existing Web pages in their browsers, while modified contents are reflected to other users in real-time. In this paper, we present the application of WFE to a cloud computing environment as well as its advantages. The environment chosen is Google App Engine, which is a platform for developing Web applications. Our comparison experiments show that we can achieve this by using push technology to perform synchronization.

Structuring Japanese Regional Information Gathered from the Web as Linked Open Data for Use in Concern Assessment

We are developing an eParticipation web platform based on Linked Open Data that targets regional communities in Japan. To increase transparency and public participation, we aim to utilize web contents related to target regions for sharing public concerns among citizens, government officials, and experts. We have designed a Linked Open Data set called SOCIA (Social Opinions and Concerns for Ideal Argumentation) to structure regional web contents (e.g. regional news articles, microblog posts, and minutes of city council meetings) and utilize them for eParticipation and concern assessment. The web contents are semi-automatically structured by our text mining system, Sophia, on the basis of regions and events extracted from news articles on the web. Minutes of city council meetings stored in SOCIA are annotated with discourse salience in order to visualize topic transitions in a meeting transcript. We also developed a prototype debate support system called citispe@k that uses SOCIA to help citizens share their concerns. Users can submit agendas, ideas, questions, and answers by referencing the structured regional information in SOCIA. Moreover, they can annotate SOCIA data with tags representing criteria for assessing concerns or utterance intentions.

Intelligent page recommender agents: real-time content delivery for articles and pages related to similar topics

In this paper, we present an architecture and sample implementation of a system which allows us to push latest up-to-date related contents to any Web news article or page in real-time. The architecture makes use of page Agents which recommend the contents and are persistent as well as synchronized over all page instances in browsers. The Agents are easy to incorporate on any Web page and make use of state-of-the-art Web technology. In our sample implementation, we show how our Agents, coupled with a Complementary Naive Bayes classifier, can recommend latest contents related to 47 Japanese prefectures and over 1700 Japanese cities. We show performance results and conclude on further research to improve the affiliate and user experience on the Web.

An Improvement for Naive Bayes Text Classification Applied to Online Imbalanced Crowdsourced Corpuses

In order to be able to use the advantage of public corpuses such as Wikipedia to address problems of classification by hierarchically structured topics with a large amount of classes, we propose an improvement of Naive Bayes based text classification algorithms which we call Semantically-Aware Hierarchical Balancing. SAHB addresses two issues in that specific use case with real-world applications, namely the large amount of topic labels to classify against, and the lack of balance in the hierarchy of the corpuses. This meta-algorithm performs with better accuracy and log-time complexity than straightforward naive bayes text classification methods or specific document weighing techniques, whilst taking equivalent time to train, which makes it more efficient, and also scalable to process and classify big data.

Differential Synchronizaiton Mechanism for a Real-Time Collaborative Web Page Editing System WFE-S

We propose a differential synchronization mechanism for Real-Time Collaborative Editing. We are developing WFE, a system for Real-Time Collaborative Editing for existing Web pages. We need to improve the response time to reduce conflicts among multiple users. We develop a DOM tree based differential updating mechanism to minimize update information for real-time editing. We implement the method on Google App Engine. We present comparison experiments that show our method can achieve practical this.

Gathering Public Concerns from Web Towards Building Corpus of Japanese Regional Concerns

Importance of concern assessment has been increased in Japanese regional communities. We have developed an e-Participation web platform based on a Linked Open Data set called SOCIA (Social Opinions and Concerns for Ideal Argumentation). To sophisticate text mining technologies for supporting concern assessment, building a corpus of public concerns is an urgent task. There are two issues to utilize the dataset SOCIA as a corpus: (1) it is required to manage reliability of annotation and (2) to filter out noisy text not relevant to public concerns. To address these research issues, (1) we incorporate schema for describing meta-context information of annotation, that is, who is annotator, whether the annotator is a human or a software agent, and how reliable the annotation is. Furthermore, (2) we investigate the difference between features of concerns and that of non-concerns in Japanese microblog posts (i.e., tweets). Through the investigation, we address sample selection bias by formulating a novel metric for ranking features, i.e., bias-penalized information gain (BPIG).

Architecture for automated search and negotiation in affiliation among community websites and blogs

In this paper, we present a multi-agent architecture which can reduce users load when searching for affiliates in a network of community websites. We give a precise definition of the environment, networks of community websites. The systems architecture is designed with scalability and easy interfacing for brokers and matchmakers in mind.We have developed a simulator to see how sites or blogs evolve with affiliation. We also show an example of its output results after a 1500-iteration long experiment on a network of community blogs. In our conclusion, we state several applications of critical interest and further research paths on the subject.