Makoto Okazaki's research while affiliated with The University of Tokyo and other places

Publications (3)

Article
Twitter has received much attention recently. An important characteristic of Twitter is its real-time nature. We investigate the real-time interaction of events such as earthquakes in Twitter and propose an algorithm to monitor tweets and to detect a target event. To detect a target event, we devise a classifier of tweets based on features such as...
Chapter
Twitter, a popular microblog service, has received much attention recently. An important characteristic of Twitter is its real-time nature. However, to date, integration of semantic processing and the real-time nature of Twitter has not been well studied. As described herein, we propose an event notification system that monitors tweet (Twitter mess...
Conference Paper
Full-text available
Twitter, a popular microblogging service, has received much attention recently. An important characteristic of Twitter is its real-time nature. For example, when an earthquake occurs, people make many Twitter posts (tweets) related to the earthquake, which enables detection of earthquake occurrence promptly, simply by observing the tweets. As descr...

Citations

... In the social networks approach to information acquisition, users' tweets have been used to identify locations that need emergency assistance (Phengsuwan et al. 2021;Wang and Ye, 2018). Besides, to detect the occurrence of a new disaster, tweets are used based on keywords, the number of words, and their context (Sakaki et al. 2012). Twitter has also been used to trigger tsunami warnings (Carley et al. 2016). ...
... The main reason for this is that the data is published on these platforms in different types such as images, texts, videos, in large volumes, by millions of people at the same time. For this reason, researchers or institutions who see Twitter as a data source and advantage, or profit factor have sought different ways to analyze the data [5][6]. Therefore, in this paper, we propose to analyze the responses of women to violence against women by extracting the views of people on Twitter with topic modeling techniques. ...
... (Liu et al. 2010;Sakaki et al. 2010;Bapna et al. 2018;Chua et al. 2019)] are difficult (or even impossible) to apply in context-specific situations, because they rely on complex algorithms [i.e., K-means, hard mo-VMF, Kalman filter and support vector machine algorithm(Sakaki et al. 2010;Rosa et al. 2011)], or they have a large dependence on external lexical sources [i.e., WordNet, Word2Vec, Wikipedia, NLTK library, Apache Lucene index, SenseClusters(Banerjee et al. 2007;Liu et al. 2010;Navigli and Lapata 2010)], to interpret semantic data. To address these challenges, the developed framework uses a cleaning database and an algorithm to perform the semantic analysis. ...