- 著者
- Yoshida Mitsuo Arase Yuki
- 出版者
- Springer Berlin Heidelberg
- 雑誌
- Information Retrieval Technology (ISSN:03029743)
- 巻号頁・発行日
- vol.7675, pp.138-149, 2012-12
- 被引用文献数
- 1
We propose a method for classifying queries whose frequency spikesin a search engine into their topical categories such as celebrities and sports. Unlikeprevious methods using Web search results and query logs that take a certainperiod of time to follow spiking queries, we exploit Twitter to timely classifyspiking queries by focusing on its massive amount of super-fresh content. Theproposed method leverages unique information in Twitter—not only tweets butalso users and hashtags. We integrate such heterogeneous information in a graphand classify queries using a graph-based semi-supervised classification method.We design an experiment to replicate a situation when queries spike. The resultsindicate that the proposed method functions effectively and also demonstrate thataccuracy improves by combining the heterogeneous information in Twitter.
- 著者
- Ozeki Kayoko Noda Tatsuya Nakamura Mieko Ojima Toshiyuki
- 出版者
- Springer Berlin Heidelberg
- 雑誌
- International Journal of Biometeorology (ISSN:00207128)
- 巻号頁・発行日
- vol.59, no.4, pp.447-451, 2014-06-19
- 被引用文献数
- 19
Background It is widely recognized that weather changes can trigger headache onset. Most people who develop headaches choose to self-medicate rather than visit a hospital or clinic. We investigated the association between weather and headache onset using large-sample sales of the headache medicine, loxoprofen. Methods We collected daily sales figures of loxoprofen and over-the-counter drugs over a 1-year period from a drug store chain in western Shizuoka prefecture, Japan. To adjust for changes in daily sales of loxoprofen due to social environmental factors, we calculated a proportion of loxoprofen daily sales to over-the-counter drug daily sales. At the same time, we obtained weather date for the study region from the website of the Japan Meteorological Agency. We performed linear regression analysis to ascertain the association between weather conditions and the loxoprofen daily sales proportion. We also conducted a separate questionnaire survey at the same drug stores to determine the reason why people purchased loxoprofen. Results Over the study period, we surveyed the sale of hundreds of thousands of loxoprofen tablets. Most people purchased loxoprofen because they had a headache. We found that the sales proportion of loxoprofen increased when average barometric pressure decreased, and that precipitation, average humidity, and minimum humidity increased on loxoprofen purchase days compared to the previous day of purchases. Conclusions This study, performed using a large dataset that was easy-to-collect and representative of the general population, revealed that sales of loxoprofen, which can represent the onset and aggravation of headache, significantly increased with worsening weather conditions.