Takako Hashimoto

A TV program generation system using digest video scenes and a scripting markup language

This paper describes a TV program generation system using digest video scenes that are retrieved from video streams with the program indexes. The key features of the system are: (1) TV programs can be dynamically generated from digest video scenes selected by user preference. (2) Directions can be added using a happiness or sadness level based on the user preferences. (3) Personalized TV programs for an individual viewer can be made. The procedures taken by the system are as follows: (1) Conjunctive expressions between scenes are automatically generated; (2) Emotional expressions are automatically generated by user preference; (3) TV program metaphors are defined; (4) Direction templates corresponding to the metaphors are defined; (5) These expressions and definitions are coded using a markup language, and (6) Contents such as virtual characters and movies are synchronized. The resultant program can be shown on a TV set.

Topic Extraction Analysis for Monetary Policy Minutes of Japan in 2014

In this paper, we will analyze monetary policy of the Bank of Japan, the central bank of Japan, just after the sales tax hike held in April 2014, through November 2014. The period matches the Japan’s turning point to the recession owing to the sales tax hike in April 2014. With the Abe second Cabinet which started in December 2012, the Bank set the “price stability target” at 2 percent. We analyzed the Monetary Policy Meeting minutes by text mining technologies. Especially we conducted a topic extraction using the Latent Dirichlet Allocation model from the Meeting minutes. The extracted topics clearly showed the impact of the sale tax hike. The biggest topic was the economic conditions related topic and its ratio peaks corresponded to the time of Japan’s GDP data released. In addition, we found that the money easing policy topic ratio increased after the tax hike and that the economic growth related topic ratio showed the decline after the tax hike.

Discovering Topic Transition about the East Japan Great Earthquake in Dynamic Social Media

Once a disaster occurs, people discuss various topics in social media such as electronic bulletin boards, SNSs and video services, and their decision-making tends to be affected by discussions in social media. Under the circumstance, a mechanism to detect topics in social media has become important. This paper targets the East Japan Great Earthquake, and proposes a time series topic transition discovering method in social media. Our proposed method adopts directed graphs to show topic structures in social media, and then form clusters using modularity measure which expresses the quality of a division of a network into modules or communities. The method computes topic transition using the Matthews correlation coefficient which is a measure of the quality of two binary classifications, and analyzes them over time. An experimental result using actual social media data about the East Japan Great Earthquake is shown as well.

Rumor analysis framework in social media

When a disaster occurred, people try to acquire information through social media such as electronic bulletin boards, SNSs, and video services. Their decision-making tend to be affected by social media information. Sometimes, social media information is useful, so people can get valuable knowledge. On the other hand, social media information is occasionally unreliable. Harmful rumors spread and cause people to panic. In todays information oriented society, a mechanism to detect rumor information in social media has become very important. This paper proposes a framework to detect the rumor information in social media. Our proposed framework clarifies topics in social media, visualizes topic structures in time series variation. Then it extracts rumor candidates and seeks related information from other media such as TV program, newspapers and so on in order to confirm the reliability of rumor candidates. By our framework, potential rumors will be shown.

Semantics extraction from social computing: a framework of reputation analysis on buzz marketing sites

Social computing services, which enable people to easily communicate and effectively share the information through the Web, have rapidly spread recently. In the marketing research domain, buzz marketing sites as social computing services have become important in recognizing the reputation of products hold with users. This paper proposes a reputation analysis framework for the buzz marketing sites. Our framework consists of four steps: the first is to extract the topics of the product using natural language processing. The input data comprises consumer messages on buzz marketing sites. Next, important topics on the products are extracted. The third step is to detect emerging consumer needs by identifying new burst topics. Finally, the results are visualized. Based on our framework, product characteristics and emerging consumer needs are extracted and reputations are visualized.

A framework for user aware route selection in pedestrian navigation system

With the help of fast and cheap information technology GPS navigators for car navigation are becoming very common. But unlike vehicle users, pedestrians form a more heterogeneous group having different levels of physical abilities with varieties of conditions, personal preferences and needs. The lack of data to support pedestrian navigation also imposes a harder challenge to design generalized navigation system for pedestrians, specially elders and persons with disability. In this work a framework for an user aware pedestrian navigation system is designed in which a fuzzy set theory based algorithm is proposed to analyze the users requirement from the linguistic expression within limited vocabulary and a genetic algorithm is proposed to generate multiple alternate near optimal routes according to users need. The optimal route can be decided by user from the options by an interactive mode. A simple simulation experiment has been done to study the feasibility of the development of an user aware, flexible pedestrian navigation system.

Personalized digests of sports programs using intuitive retrieval and semantic analysis

Recently, digital broadcasting has experienced rapid growth. Digital broadcasting can deliver additional data as program attachments, which viewers can use to flexibly browse and retrieve parts of the program on their TV-receiving terminals. They can also make personalized digests from the broadcast TV programs. This function is particularly useful for viewers of sports programs because the digests reflect varied viewer preferences, such as favorite teams and players. This paper presents a method for making personalized digests for sports programs using additional data attachments.

Social media analysis determining the number of topic clusters from buzz marketing site

Social media, which enable people to easily communicate and effectively share the information through the web, are rapidly spreading recently. In such media, effective topic extraction technique from messages has been significant so that trend topics and their reputation can be recognised. However, since messages contain redundancy and topic boundaries are ambiguous, it is difficult to extract appropriate topics. As the first step for topic extraction, this paper proposes an effective measure to automatic determination of appropriate number of topics based on the intra-cluster distance and the inter-cluster distance among topic clusters. We present our experimental results to show the effectiveness of our proposed approach.

A Rule-Based Scheme to Make Personal Digests from Video Program Meta Data

Content providers have recently started adding a variety of meta data to various video programs; these data provide primitive descriptors of the video contents. Personal digest viewing that uses the meta data is a new application in the digital broadcasting era. To build personal digests, semantic program structures must be constructed and significant scenes must be identified. Digests are currently made manually at content provider sites. This is time-consuming and increases the cost. This paper proposes a way to solve these problems with a rule-based personal digest-making scheme (PDMS) that can automatically and dynamically make personal digests from the meta data. In PDMS, depending on properties of the video program contents and viewer preferences, high-level semantic program structures can be constructed from the added primitive meta data and significant scenes can be extracted. The paper illustrates a formal PDMS model. It also presents detailed evaluation results of PDMS using the contents of a professional baseball game TV program.

Event Detection from Millions of Tweets Related to the Great East Japan Earthquake Using Feature Selection Technique

Social media offers a wealth of insight into howsignificant events -- such as the Great East Japan Earthquake, the Arab Spring, and the Boston Bombing -- affect individuals. The scale of available data, however, can be intimidating: duringthe Great East Japan Earthquake, over 8 million tweets weresent each day from Japan alone. Conventional word vector-based event-detection techniques for social media that use Latent SemanticAnalysis, Latent Dirichlet Allocation, or graph communitydetection often cannot scale to such a large volume of data due to their space and time complexity. To alleviate this problem, we propose an efficient method for event detection by leveraging a fast feature selection algorithm called CWC. While we begin withword count vectors of authors and words for each time slot (inour case, every hour), we extract discriminative words from eachslot using CWC, which vastly reduces the number of features to track. We then convert these word vectors into a time series of vector distances from the initial point. The distance betweeneach time slot and the initial point remains high while an eventis happening, yet declines sharply when the event ends, offeringan accurate portrait of the span of an event. This method makes it possible to detect events from vast datasets. To demonstrateour methods effectiveness, we extract events from a dataset ofover two hundred million tweets sent in the 21 days followingthe Great East Japan Earthquake. With CWC, we can identifyevents from this dataset with great speed and accuracy.