1 Fig. 1 To calculate calorie diet diary. Comprehensive health support site. Eat Smart. SNS 2 [3] 2. c 2012 Information Processing Society of

Size: px

Start display at page:

Download "1 Fig. 1 To calculate calorie diet diary. Comprehensive health support site. Eat Smart. SNS *2 [3] 2. * c 2012 Information Processing Society of"

ふさこあざみ
5 years ago
Views:

1 1,a) 1 2 2, , Log-based Assessment for the Success and Failure of Dieting Jun Iio 1,a) Shiro Udoguchi 1 Yoshihiro Koyama 2 Yuko Hasegawa 2, 1 Received: November 8, 2011, Accepted: September 10, 2012 Abstract: The web application named Eat Smart provides functions for its users to keep dietary records, exercise programs, daily comments, and other information, as the functions to support the users activities for dieting. Although these functions are considered effective in dieting, we have found the users are divided into two groups; the one is the users who have succeeded in dieting and the other is the users who have not succeeded. Therefore, this study aimed to clarify what was important in effective dieting, by analyzing the information recorded by each user. As a result, it was confirmed that the expression of users firm intention in dieting was clearly expressed in the records, and that there was possibility to improve the supportive service for dieting. Keywords: supportive service for dieting, log-based assesment, text mining, diary analysis, diet record analysis 1. [1] 1 Mitsubishi Research Institute, Inc., Chiyoda, Tokyo , Japan 2 Eat Smart Eat Smart, Inc., Shibuya, Tokyo , Japan 1 Presently with Tokyo University of Agriculture a) iiojun@mri.co.jp DICOMO ICT ASP [2] 1 *1 1 *1 c 2012 Information Processing Society of Japan 2624

2 1 Fig. 1 To calculate calorie diet diary. Comprehensive health support site. Eat Smart. SNS *2 [3] 2. * c 2012 Information Processing Society of Japan 2625

3 2 Fig. 2 Examples of user data which is determined as succeeded or failure in dieting kg 0kg 30 kg 1 8, (1) [4] (2) (3) (4) (5) c 2012 Information Processing Society of Japan 2626

4 (3) (4) (5) (5) ,299 1, ,254 3, [5] (3) 25 3 (2) 1 Table 1 Classifing success and failure group. % % % , Table 2 Classifing success and failure group diary. / 354 8, , , c 2012 Information Processing Society of Japan 2627

5 Table 3 3 Words which have different occurrence rate in each group. Gr Gr Gr Gr Fig. 3 3 Two examples of user diary; an ideal one (left) and an inadequate one (right). (4) (5) (5) c 2012 Information Processing Society of Japan 2628

6 4 Table 4 Mean and standard deviation of number of entries in each diary which contain each word. Gr [μ/σ] Gr [μ/σ] Gr [μ/σ] Gr [μ/σ] (5) (5) / % χ 2 = p = c 2012 Information Processing Society of Japan 2629

7 5 Table 5 Classifing success and failure group food log. / ,465 1,187 1,359 8, ,948 1,490 1,809 10,268 1,054 1,364,413 1,295 1,539 Table 6 6 Items in the food-log which have different occurrence rate in each group. Gr Gr Gr Gr ml ,737 10, c 2012 Information Processing Society of Japan 2630

8 4 Fig. 4 Co-occurrence graph; success group (left) and failure group (right) [6] 4 KH Coder [7] 5. [8] c 2012 Information Processing Society of Japan 2631

9 [9] [10] SNS SNS Newman [11] [12] SNS 1 IC [14] IC [13] [15] [16] FoodLog *3 FoodLog Preuveneers [17] Luo [18], [19] [18] Web [19] [19] Wiesner [20] Wikipedia 6. 1, *3 c 2012 Information Processing Society of Japan 2632

10 [1] Vol.94, pp (2006). [2] ASP ASPVol.91, No.12, pp (2009). [3] (2007). [4] version (2003). [5] 3 (4) 3) pp (2007). [6] Nanri, A., Mizoue, T., Noda, M., Takahashi, Y., Kato, M., Inoue, M. and Tsugane, S.: Rice Intake and Type 2 Diabetes in Japanese Men and Women: The Japan Public Health Center-based Prospective Study, American Journal of Clinical Nutrition, Vol.92, No.6, pp (2010). [7] 2 Vol.19, No.1, pp (2004). [8] Vol.49, No.2, pp (2008). [9] DPS Vol.2008, No.54, pp (2008). [10] Vol DPS-142, No.50, pp.1 8 (2010). [11] Newman, M.W., Lauterbach, D., Munson, S.A., Resnick, P. and Morris, M.E.: It s not that I don t Have Problems, I m Just not Putting them on Facebook: Challenges and Opportunities in using Online Social Networks for Health, Proc. ACM 2011 Conference on Computer Supported Cooperative Work (CSCW 11), pp (Mar. 2011). [12] e- DD Vol.2008, No.10, pp.1 6 (2008). [13] IHISS Vol.2009-DPS-140, No.5, pp.1 5 (2009). [14] IC LAN Vol.2010-CE-107, No.3, pp.1 8 (2010). [15] Vol.2011-MBL-57, No.5, pp.1 8 (2011). [16] Food Logging and Processing Analysis of Food Images Vol.63, No.3, pp (2009). [17] Preuveneers, D. and Berbers, Y.: Mobile Phones Assisting with Health Self-care: A Diabetes Case Study, Proc. 10th International Conference on Human Computer Interaction with Mobile Devices and Services (Mobile- HCI 08), pp (Sep. 2008). [18] Luo, G. and Tang, C.: Automatic Home Nursing Activity Recommendation, Proc. AMIA Annual Symposium, pp (Nov. 2009). [19] Luo, G., Tang, C. and Thomas, S.B.: Intelligent personal health record: Experience and open issues, Proc. 1st ACM International Health Informatics Symposium (IHI 10 ), pp (Nov. 2010). [20] Wiesner, M. and Pfeifer, D.: Adapting Recommender Systems to the Requirements of Personal Health Record Systems, Proc. 1st ACM International Health Informatics Symposium (IHI 10 ), pp (Nov. 2010). c 2012 Information Processing Society of Japan 2633

11 HCD-Net Eat Smart Eat Smart ASP c 2012 Information Processing Society of Japan 2634

SNS 3) 4) kg kg 3kg 1 8, user32172 user69342 user user4243 user27

SNS 3) 4) kg kg 3kg 1 8, user32172 user69342 user user4243 user27 ? 1 1 2 2 1. 1) 1 ICT ASP 2) 1 1 1 Log-based Assessment of the Underlying Reasons for the Success and Failure of Dieting Jun Iio, 1 Shiro Udoguchi, 1 Yoshihiro Koyama 2 and Yuko Hasegawa 2 The web application