近年來，智慧型裝置的快速成長，人們會透過智慧型裝置裡的應用程式查
詢美食餐廳、優惠卷，甚至是記錄一周的生活作息及查看即時路況，由此可知
應用程式已成為現代人生活不可或缺的一環。
要如何在這麼多的應用程式當中找到屬於我們的價值，是我們需要思考的
問題，在此提出的應用程式不但提供美食推薦系統，推薦評價較好的餐廳給使
用者，更提供個人行為的紀錄，以便使用者回顧一周的點滴，甚至可以近一步
進行時間管理和規劃。
在此論文中著重在美食推薦系統，推薦系統是一個熱門且普遍的話題，在
五花八門的餐廳中，要如何把評價較好的餐廳推薦給使用者，是一個重要的問
題，這篇論文中，首先，利用Machine Learning 的方法訓練有關美食的辭庫，
再來分別透過Support Vector Machine(SVM) 和較直覺的方法來分析文章，並
且藉由分析的結果當作評分依據，最後將詳細描述應用程式的架構，其中包括
應用程式介面、演算法和模擬結果。

In recent years, according to the rapid growth of the smart devices, people use
different applications on the smart devices to find restaurants, coupons, even to
record their weekly time table and to check the real-time traffic status; from above
tells that applications on the smart devices have became an indispensable thing
for people in nowadays.
The question for us is ”How do we find our value from all these different
kind of applications?” The application we present not only provides restaurant
recommendation system, recommending high-reviews restaurants for users, but
also provides personal behavior records for users to review every weekly details
and even get to plan and manage the time of use.
In this paper, we focus more on the restaurant recommendation system, recommendation
system is a popular and common topic. The biggest task is how to
recommend high-reviews restaurants in a motley variety of restaurants. We wish
to decide high evaluation restaurants based on analyze the articles of food. First,
the jieba Chinese text segmentation was employed to accomplish the text segmentation
task. Then, we are training lexicon about foods, and analyze an article by
using support vector machine (SVM) algorithm and intuitive method. Finally,
we use the results of the analysis as the grade basis. In the following chapters,
we will describe application framework in detail including the user interface of
application, algorithm, system architecture, and simulation results.

Bibliography
[1] ”Yelp official website,” Yelp, [Online]. Available:
http://www.yelp.com.tw/
[2] ”Download the Voice Go,” Voice Go, [Online]. Available:
https://play.google.com/store/apps/details?id=com.cyberon.android.voicego
[3] ”Download the Food Convenient,” Food Convenient, [Online]. Available:
https://play.google.com/store/apps/details?id=com.orangefish.app.delicacy
[4] ”PTT website,” PTT, [online]. Available:
https://www.ptt.cc/bbs/Food/index.html
[5] Support vector machine. https://en.wikipedia.org/wiki/Support_ vector_
machine. Accessed June 28, 2015.
[6] Tong, Simon, and Daphne Koller. ”Support vector machine active learning
with applications to text classification.” The Journal of Machine Learning
Research 2 (2002): 45-66.
[7] Pedregosa, Fabian, et al. ”Scikit-learn: Machine learning in Python.” The
Journal of Machine Learning Research 12 (2011): 2825-2830.
[8] Jieba chinese text segmentation. https://github.com/fxsjy/jieba. Accessed
June 28, 2015.
[9] ”iPeen website,” iPeen, [online]. Available:
http://www.ipeen.com.tw/
[10] JSON. https://en.wikipedia.org/wiki/JSON. Accessed June 28, 2015
29
[11] Latent semantic analysis. https://en.wikipedia.org/wiki/Latent_ semantic_
analysis. Accessed June 28, 2015.
[12] Baharudin, Baharum, Lam Hong Lee, and Khairullah Khan. ”A review of
machine learning algorithms for text-documents classification.” Journal of advances
in information technology 1.1 (2010): 4-20.
[13] Bag-of-words model. https://en.wikipedia.org/wiki/Bag-of-words_ model.
Accessed by June 28, 2015.
[14] SALTON, Gerard; WONG, Anita; YANG, Chung-Shu. A vector space model
for automatic indexing. Communications of the ACM, 1975, 18.11: 613-620.
30