Tomohiro Fukuhara

Ubiquitous Memories: a memory externalization system using physical objects

In this paper we propose an object-triggered human memory augmentation system named “Ubiquitous Memories” that enables a user to directly associate his/her experience data with physical objects by using a “touching” operation. A user conceptually encloses his/her experiences gathered through sense organs into physical objects by simply touching an object. The user can also disclose and re-experience for himself/herself the experiences accumulated in an object by the same operation. We implemented a prototype system composed basically of a radio frequency identification (RFID) device. Physical objects are also attached to RFID tags. We conducted two experiments. The first experiment confirms a succession of the “encoding specificity principle,” which is well known in the research field of psychology, to the Ubiquitous Memories system. The second experiment aims at a clarification of the system’s characteristics by comparing the system with other memory externalization strategies. The results show the Ubiquitous Memories system is effective for supporting memorization and recollection of contextual events.

Applying a Burst Model to Detect Bursty Topics in a Topic Model

This paper focuses on two types of modeling of information flow in news stream, namely, burst analysis and topic modeling. First, when one wants to detect a kind of topics that are paid much more attention than usual, it is usually necessary for him/her to carefully watch every article in news stream at every moment. In such a situation, it is well known in the field of time series analysis that Kleinberg’s modeling of bursts is quite effective in detecting burst of keywords. Second, topic models such as LDA (latent Dirichlet allocation) are also quite effective in estimating distribution of topics over a document collection such as articles in news stream. However, Kleinberg’s modeling of bursts is usually applied only to bursts of keywords but not to those of topics. Considering this fact, we propose how to apply Kleinberg’s modeling of bursts to topics estimated by a topic model such as LDA and DTM (dynamic topic model).

Web content summarization using social bookmarks: a new approach for social summarization

An increasing number of Web applications are allowing users to play more active roles for enriching the source content. The enriched data can be used for various applications such as text summarization, opinion mining and ontology creation. In this paper, we propose a novel Web content summarization method that creates a text summary by exploiting user feedback (comments and tags) in a social bookmarking service. We had manually analyzed user feedback in several representative social services including del.icio.us, Digg, YouTube, and Amazon.com. We found that (1) user comments in each social service have its own characteristics with respect to summarization, and (2) a tag frequency rank does not necessarily represent its usefulness for summarization. Based on these observations, we conjecture that user feedback in social bookmarking services is more suitable for summarization than other type of social services. We implemented prototype system called SSNote that analyzes tags and user comments in del.icio.us, and extracts summaries. Performance evaluations of the system were conducted by comparing its output summary with manual summaries generated by human evaluators. Experimental results show that our approach highlights the potential benefits of user feedback in social bookmarking services.

Analysing features of Japanese splogs and characteristics of keywords

This paper focuses on analyzing (Japanese) splogs based on various characteristics of keywords contained in them. We estimate the behavior of spammers when creating splogs from other sources by analyzing the characteristics of keywords contained in splogs. Since splogs often cause noises in word occurrence statistics in the blogosphere, we assume that we can efficiently (manually) collect splogs by sampling blog homepages containing keywords of a certain type on the date with its most frequent occurrence. We manually examine various features of collected blog homepages regarding whether their text content is excerpt from other sources or not, as well as whether they display affiliate advertisement or out-going links to affiliated sites. Among various informative results, it is important to note that more than half of the collected splogs are created by a very small number of spammers.

An empirical study on selective sampling in active learning for splog detection

This paper studies how to reduce the amount of human supervision for identifying splogs / authentic blogs in the context of continuously updating splog data sets year by year. Following the previous works on active learning, against the task of splog / authentic blog detection, this paper empirically examines several strategies for selective sampling in active learning by Support Vector Machines (SVMs). As a confidence measure of SVMs learning, we employ the distance from the separating hyperplane to each test instance, which have been well studied in active learning for text classification. Unlike those results of applying active learning to text classification tasks, in the task of splog / authentic blog detection of this paper, it is not the case that adding least confident samples peforms best.

Analyzing concerns of people from Weblog articles

A system for analyzing concerns of people from Weblog articles is proposed. The system called KANSHIN analyzes concerns of people by collecting Japanese, Chinese, and Korean Weblog articles. Users can find concerns of people in each language. Users can also compare differences of concerns between Japanese, Chinese, and Korean language communities. We describe several analysis results: (1) patterns of social concerns, (2) change of focuses on a problem along with the time, (3) differences of concerns on a problem between Japanese, Chinese, and Korean Weblog sites, and (4) relation between words in Weblog articles and real world natural phenomenon.

Proposal of Handover System for Care Workers Using Community Intelligence

The experience and intuition gathered over many years of employment are extremely important for providing high-quality service in the fields of nursing and care. However, these experience and intuition are subjective, making it difficult to pass on experience and related know-how to a novice. To realize such field community intelligence, we have taken the approach that presenting records taken by other workers and their procedures will foster increased communication among workers and that, in doing so, knowledge and know-how will flow naturally among them. Consequently, by structuring the recorded information according to the work context, systematically organized knowledge can be exchanged and circulated. This chapter describes the handover system prototypes that can realize community intelligence by changing the handover workflow.

Mining Cross-Lingual/Cross-Cultural Differences in Concerns and Opinions in Blogs

The goal of this paper is to cross-lingually analyze multilingual blogs collected with a topic keyword. The framework of collecting multilingual blogs with a topic keyword is designed as the blog feed retrieval procedure. Mulitlingual queries for retrieving blog feeds are created from Wikipedia entries. Finally, we cross-lingually and cross-culturally compare less well known facts and opinions that are closely related to a given topic. Preliminary evaluation results support the effectiveness of the proposed framework.

LDA-Based topic modeling in labeling blog posts with wikipedia entries

Given a search query, most existing search engines simply return a ranked list of search results. However, it is often the case that those search result documents consist of a mixture of documents that are closely related to various contents. In order to address the issue of quickly overviewing the distribution of contents, this paper proposes a framework of labeling blog posts with Wikipedia entries through LDA (latent Dirichlet allocation) based topic modeling. More specifically, this paper applies an LDA-based document model to the task of labelling blog posts with Wikipedia entries. One of the most important advantages of this LDA-based document model is that the collected Wikipedia entries and their LDA parameters heavily depend on the distribution of keywords across all the search result of blog posts. This tendency actually contributes to quickly overviewing the search result of blog posts through the LDA-based topic distribution. In the evaluation of the paper, we also show that the LDA-based document retrieval scheme outperforms our previous approach.

KANSHIN: A Cross-Lingual Concern Analysis System Using Multilingual Blog Articles

An architecture of cross-lingual concern analysis (CLCA) using multilingual blog articles, and its prototype system are described. As various people who are living in various countries use the Web, cross-lingual information retrieval (CLIR) plays an important role in the next generation search. In this paper, we propose a CLCA as one of CLIR applications for facilitating users to find concerns of people across languages. We propose a layer architecture of CLCA, and its prototype system called KANSHIN. The system collects Japanese, Chinese, Korean, and English blog articles, and analyzes concerns across languages. Users can find concerns from several viewpoints such as temporal, geographical, and a network of blog sites. The system also facilitates users to browse multilingual keywords using Wikipedia, and the system facilitates users to find spam blogs. An overview of the CLCA architecture and the system are described.