fontsize
Search

Undergraduate and Graduate Schools

Home > Undergraduate and Graduate Schools > Faculty Members List > Department of Computer Science and Engineering > Mitsuo Yoshida

Mitsuo Yoshida

Affiliation Department of Computer Science and Engineering
Title Assistant Professor
Fields of Research Web Engineering / Natural Language Processing / Computational Social Science / Information Retrieval
Degree Ph.D. in Engineering (University of Tsukuba)
Academic Societies Information Processing Society of Japan / The Japanese Society for Artificial Intelligence / The Association for Natural Language Processing / The Database Society of Japan
E-mail yoshida@cs
Please append ".tut.ac.jp" to the end of the address above.
Laboratory website URL http://www.cs.tut.ac.jp/~yoshida/
Researcher information URL Researcher information

Theme1:Data Mining on Social Media

Overview

Academic information has been evaluated by citation-based indicators such as the Impact Factor and h-index. Since around 2010, mentions in social media have been used instead of citation-based indicators. These indicators are called “Altmetrics”. We reported the trend of mentions for Japanese academic information in social media and discussed the future outlook.

Selected publications and works

Mitsuo Yoshida. New Challenge for Bibliometrics : Development of the Altmetrics Measurement Service. The Journal of Information Science and Technology Association (in Japanese). vol.64, no.12, pp.501-507, 2014.

Theme2:Search Query Classification

Overview

We propose a method for classifying queries whose frequency spikes in a search engine into their topical categories such as celebrities and sports. Unlike previous methods using Web search results and query logs that take a certain period of time to follow spiking queries, we exploit Twitter to timely classify spiking queries by focusing on its massive amount of super-fresh content. The proposed method leverages unique information in Twitter - not only tweets but also users and hashtags. We integrate such heterogeneous information in a graph and classify queries using a graph-based semi-supervised classification method. We design an experiment to replicate a situation when queries spike. The results indicate that the proposed method functions effectively and also demonstrate that accuracy improves by combining the heterogeneous information in Twitter.

Selected publications and works

Mitsuo Yoshida, Yuki Arase. Trend Query Analysis on Heterogeneous Web Resources. IPSJ Transactions on Databases (in Japanese). vol.9, no.1, pp.20-30, 2016.
Mitsuo Yoshida, Yuki Arase, Takaaki Tsunoda, Mikio Yamamoto. Wikipedia Page View Reflects Web Search Trend. The 2015 ACM Web Science conference (WebSci15). Oxford, UK, June 28 - July 1, 2015. (arXiv.org)
Mitsuo Yoshida, Yuki Arase. Trend Query Classification using Label Propagation. Transactions of the Japanese Society for Artificial Intelligence (in Japanese). vol.30, no.1, pp.161-171, 2015.
Mitsuo Yoshida, Yuki Arase. Exploiting Twitter for Spiking Query Classification. Proceeding of the Eighth Asia Information Retrieval Societies Conference. LNCS, vol.7675, pp.138-149, 2012.

Theme3:Primary Content Extraction from Web Pages

Overview

In recent years, the proportion of primary content in a Web page has been decreasing as content management systems (CMS's) continue to spread, because CMS's automatically and excessively add unnecessary parts such as menus, advertisements and copyright notices into the Web page. We proposed a simple method extracting the primary content from a collection of Web pages without training data.We regard a Web page as a set of blocks (minimum unit of primary or non-primary content), and assume that blocks of the primary content are unique and there are copies of those of non-primary content.Additionally, we proposed a simple method to generate special CSS selectors as rules of extracting primary content from a collection of Web pages. We showed that the proposed method can accurately extract the primary content from real pages of blog and news sites.

Selected publications and works

Mitsuo Yoshida, Takashi Inui, Mikio Yamamoto. Automatic Extraction of Blog Posts and Comments from Blog Pages. IPSJ Journal (in Japanese). vol.54, no.12, pp.2502-2512, 2013.
Mitsuo Yoshida, Mikio Yamamoto. Primary Content Extraction from News Pages without Training Data. DBSJ Journal (in Japanese). vol.8, no.1, pp.29-34, 2009.

Title of class

Basic Experiments in Computer Science and Engineering
Laboratory Experiments on Computer Science and Engineering


to Page top