• 沒有找到結果。

第五章、 結論

5.4 未來研究方向

本研究之目的為預測出與menu 美食誌相近的排名,以節省額外人力與時 間成本調查其排名,轉為僅需利用社群評論資料進行社群聆聽(Social Listening) 即可計算出類似於menu 美食誌的排名,因此以下將描述未來可進一步研究的 方向以改善排名預測結果:

1. 蒐集更多訓練資料進行分析:目前僅用八種 menu 美食誌的餐廳排行榜作為 訓練資料,如果能夠蒐集更多menu 美食誌的訓練資料才能更精準地篩選出不 合適的非情緒詞彙emoji,以更精準的情緒詞彙改善排名結果,或是結合更多社 群的評論資料進行分析,測試是否能增加預測精準度。

2. 機器學習分類演算法加入更多特徵值:本研究中亦實作 random forest 等監督 式機器學習演算法預測排名,但是本研究限於可從Instagram 評論中取得的特徵 值不多,因此未來若能增加更多相關特徵值,勢必能對預測結果有所幫助。

3. 試做其他具公信力的餐廳排行標準:未來研究可試著尋找與 menu 美食誌類 似具有公信力的其他知名機構之排名結果,與其比較mse 或是其他排名校正指 標,測試是否能更趨於其排名結果。

4. 翻譯評論增加準確度:若以中文的情緒詞彙進行情緒分析,將無法對各國語 言進行分析,而某些餐飲種類的Instagram 評論其中一部份為來自各國包括日 文、韓文、泰文等語言,因此若能將其語言進行翻譯,再進行情緒分析,將有 可能讓排名結果更趨向menu 美食誌的排行。

中文參考文獻

江穎 (2017)。<機器學習預測《歌手》決賽全排名>。檢自

https://zhuanlan.zhihu.com/p/26883727 (Jun.29,2020)

吳美慧 (2013)。《文章強度、部落客評價及推薦產品取得方式對購買意圖之影 響》。國立中央大學資訊管理研究所碩士論文。

金蛋網路數位行銷 (2018)。〈口碑行銷|餐廳美食爆紅關鍵:IG 打卡 +GOOGLE 評論〉。檢自

https://www.gemarketing.com.tw/article/wom/food-ig-google/

(Dec.23,2019)

馬千惠 (2012)。《網路打卡的口碑傳播效果對消費者購買決策影響之研究-以 餐飲業為例》。國立中山大學傳播管理研究所碩士論文。

陳佳雯 (2017)。《探討美食圖片內容力及社群影響力對按讚行為之影響 — 以 Instagram 為例》。國立中山大學資訊管理學系研究所碩士論文。

陳美如、蔡精育、宋鎧、范錚強 (2012)。《線上口碑對消費者購買意圖之影響

-網路論壇的實驗研究》。中山管理評論,第 20 卷,第 2 期。

游和正、黃挺豪、陳信希 (2012)。《領域相關詞彙極性分析及文件情緒分類之 研究》。Computational Linguistics and Chinese Language

Processing, 17(4),33-48。

鉅亨網新聞中心 (2015)。〈商戶點評網站 Yelp 遇困境:評分有時並不公正〉。 檢自 https://news.cnyes.com/news/id/483830 (Dec.19,2019) 結巴中文斷詞 (2016)。<結巴中文斷詞台灣繁體版本>。檢自

https://github.com/ldkrsi/jieba-zh_TW#readme (Jun.29,2020) 痞客幫 (2020)。<痞客幫社群影響力>。檢自

https://pixranking.events.pixnet.net/influence (Jun.29,2020) 愛食記 (2020)。<從超過 50,000 家精選餐廳中,探索您不知道的熱門美食>。

檢自 https://ifoodie.tw/ (Jun.29,2020)

廖敏惠 (2015)。《網路美食評論情緒分析之研究》。國立高雄餐旅大學台灣飲食 文化所產業研究所碩士論文。

網路溫度計 (2019 年 12 月 19 日)。〈美食網路口碑排行〉。檢自

https://dailyview.tw/Top100/Topic/90?volumn=0 (Dec.19,2019) 網路溫度計 (2020)。〈網路溫度計網路口碑排行榜資訊〉。檢自

https://dailyview.tw/Top100/RankInfo (Jun.29,2020)

謝佩庭 (2014)。《基於使用者情緒關鍵詞彙之臉書粉絲專頁評論分類與評分系 統》。國立交通大學多媒體工程研究所碩士論文。

戰爭熱誠 (2019)。< Python 機器學習筆記:隨機森林算法>。檢自 https://www.cnblogs.com/wj-1314/p/9628303.html (Jun.29,2020)

簡之文 (2012)。《部落格文章情感分析之研究》。淡江大學資訊管理學系碩士論 文。

Caitlin (2019)。< INSTAGRAM 新手入門:怎麼看後台的數據分析>。檢自 https://caitlin1010.pixnet.net/blog/post/311663027

(Jun.29,2020)

HackMD (2020)。<用 Markdown 即時協作知識庫>。檢自 https://hackmd.io/ (Jun.29,2020)

INSTAGRAM (2020)。<在 Instagram 查看洞察報告>。檢自

https://www.facebook.com/help/instagram/1533933820244654?help ref=uf_permalink (Jun.29,2020)

MENU 美食誌 (2020)。<吃貨必備,簡單記錄,搜尋好吃店家的美食神器>。

檢自https://menutaiwan.com/tw/about (Jun.29,2020) Wikipedia (2020)。<皮爾遜積差相關係數>。檢自

https://zh.wikipedia.org/wiki/%E7%9A%AE%E5%B0%94%E9%80%8A%E7%

A7%AF%E7%9F%A9%E7%9B%B8%E5%85%B3%E7%B3%BB%E6%95%B0 (Jun.29,2020)

西文參考文獻

An, J.X., Huang, J., Yu, W., Akoglu, L., Chandy, R., Faloutsos, C.(2011). Algorithm of Disambiguation and Matching of Chinese Word Segmentation in Connected Strategies Research. Advanced Materials Research (Volumes 219-220), 1702-1706.

Bhasin, H. (2019). Retrieved from What is Hashtag Marketing? Importance Of Hashtag Marketing https://www.marketing91.com/what-is-hashtag-marketing/

(Dec 23,2019)

Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.

Brown, D., Hayes, N. (2008). Influencer Marketing: Who Really Influences Your Customers?, Routledge.

Chaovalit, P., Zhou, L. (2005). Movie review mining: a compareson between supervised and unsupervised. In Proceedings of the 38th Hawaii International Conference on System Sciences.

Chevalier, J. A., & Mayzlin, D. (2006). The effect of word of mouth on sales: Online book reviews. Journal of Marketing Research, 43, 345–354

Dai, W., Jin, G.Z., Lee, J., Luca, M. (2018). Aggregation of Consumer Ratings: An Application to Yelp.com. Quantitative Marketing and Economics, 16(3), 289-339 Dewey, J., Wheeler, J., (2009). Interest and Effort in Education. Southern Illinois

University Press: eBook Academic Collection.

Domingos, P., Richardson, M. (2002). Mining the network value of customers. In Proceeding of the seventh ACM SIGKDD international conference on

Knowledge discovery and data mining, 57–66.

Gan, Q., Ferns, B.H., Yu, Y., Jin, L. (2017) A Text Mining and Multidimensional Sentiment Analysis of Online Restaurant Reviews. Journal of Quality Assurance

in Hospitality & Tourism, 465-492

GONG, X. (2014). Strategic Customer Engagement on Instagram- A Case of Global Business to Customer (B2C) Brands. Master’s Thesis in Media Management, Media Management Master Program KTH Royal Institute of Technology.

Jia, S. (2018). Behind the ratings: Text mining of restaurant customers’ online reviews, International Journal of Market Research, 60(6), 561–572.

Jin, J., Ji, P., Liu, Y. (2014). Recommending Rating Values on Reviews for Designers.

Encyclopedia of Business Analytics and Optimization.

Kamal, A. (2015). Review Mining for Feature Based Opinion Summarization and Visualization. International Journal of Computer Applications. 119(17)

Kaviya, K., Roshini, C., Vaidhehi, V., Dhalia Sweetlin, J. (2017) Sentiment Analysis for Restaurant Rating. IEEE International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials (ICSTM), 140-145.

Kempe, D., Kleinberg, J., Tardos, E. (2003). Maximizing the spread of influence through a social network. In the Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 137-146.

Kralj Novak, P., Smailovic, J., Sluban, B., Mozetic, I. (2015). Sentiment of Emojis.

PLoS ONE 10(12): e0144296.

Lee K, D. (2015). Analytics, Goals, and Strategy for Social Media. Library Technology Reports, 51(1), 26–32.

Ling Hang Yew, R., Binti Suhaidi, S., Seewoochurn, P., Kumar Sevamalai, V. (2018).

Social Network Influencers’Engagement Rate Algorithm Using Instagram Data.

2018 Fourth International Conference on Advances in Computing,

Communication & Automation (ICACCA).

Luca, M., Zervas, G. (2016). Fake It Till You Make It: Reputation, Competition, and Yelp Review Fraud. Management Science, 62(12),

3412-3427.https://doi.org/10.1287/mnsc.2015.2304

Luca, M. (2016). Reviews, Reputation, and Revenue: The Case of Yelp.com. Harvard Business School Working Paper, No. 12-016

Mir Riyanul Islam. (2014). Numeric Rating of Apps on Google Play Store by Sentiment Analysis on User Reviews. International Conference on Electrical Engineering and Information & Communication Technology, pp.1-4.

Moon, S., Bergey, P. K., & Iacobucci, D. (2010). Dynamic effects among movie ratings, movie revenues, and viewer satisfaction. Journal of Marketing, 74, 108–

121.

Murphy, R. (2018). Comparison of Local Review Sites: Which Platform is Growing the Fastest? Retrieved from

https://www.brightlocal.com/research/comparison-of-local-review-sites/ (Dec 23,2019)

Page, L., Brin, S., Motwani, R., Winograd, T. (1999). The PageRank Citation Ranking: Bringing Order to the Web. Technical Report. Stanford InfoLab.

Perera, I.K.C.U., Caldera, H.A. (2017). Aspect Based Opinion Mining on Restaurant Reviews. 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA), 542-546.

Peters, K., Chen, Y., Kaplan, A., Ognibeni, B., Pauwels, K. (2013). Social Media Metrics–A Framework and Guidelines for Managing Social Media. Journal of Interactive Marketing, 27, 281–298.

Pitman, J.(2019).The Ultimate Guide to Google My Business Reviews. Retrieved

from https://www.brightlocal.com/learn/how-do-google-reviews-work/ (Dec 23,2019)

Rachid, A.D., Abdellah, A., Belaid, B., Rachid, L. (2018). Clustering Prediction Techniques in Defining and Predicting Customers Defection: The Case of E-Commerce Context. International Journal of Electrical and Computer Engineering (IJECE).

Richardson, M., Domingos, P. (2002). Mining Knowledge-Sharing Sites for Viral Marketing. In Proceeding of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining.

Shih-Ming, W., Lun-Wei, K. (2016). ANTUSD:A Large Chinese Sentiment Dictionary. Language Resources and Evaluation Conference(LREC).

Yang, L., Jian-Wu, B., Zhi-Ping, F. (2017). Ranking products through online reviews:

A method based on sentiment analysis technique and intuitionistic fuzzy set theory. Information Fusion, 36, 149-161.

Yelp Elite Squad. (2014). Yelp Elite Squad. Retrieved from http://www.yelp.com/elite (Dec 23,2019)

Zizzi, Hosie, R. (2017). HOW INSTAGRAM HAS TRANSFORMED THE RESTAURANT INDUSTRY FOR MILLENNIALS. Retrieved from

https://www.independent.co.uk/life-style/food-and-drink/millenials-restaurant-how-choose-instagram-social-media-where-eat-a7677786.html (Dec 23,2019) Zhang, K., Cheng, Y., Liao, W.K., Choudhary, A. (2011). Mining millions of reviews:

a technique to rank products based on importance of reviews. Proceedings of the 13th International Conference on Electronic Commerce, ACM.

Zhu, T., Wu, B., Wang, B. (2009). Social Influence and Role Analysis Based on Community Structure in Social Network. Advanced Data Mining and

Applications, 788-795.

附錄

來源:https://findlife.com.tw/menu/blog/2019/09/23/201909italytop10/

二、牛肉麵

來源:https://findlife.com.tw/menu/blog/2019/12/01/2019beefnoodles/

三、滷肉飯

來源:https://findlife.com.tw/menu/blog/2019/12/15/2019lowbahbang/

四、咖哩料理

五、港式餐廳

來源:https://findlife.com.tw/menu/blog/2020/03/20/2019hongkongstyle/

六、韓式炸雞

來源:https://findlife.com.tw/menu/blog/2020/05/11/2020koreanchicken/

七、牛排

來源:https://findlife.com.tw/menu/blog/2020/02/27/2020steak/

八、鐵板燒

來源:https://findlife.com.tw/menu/blog/2019/10/26/2019tepanyaki/

九、冰品

來源:https://findlife.com.tw/menu/blog/2020/05/06/2020icetop10/

十、韓式料理

來源:https://findlife.com.tw/menu/blog/2020/04/19/2020koreantop10/

附錄二、 擴增情緒詞典

70 傻眼 -0.2 89 noodlelover 0.1 90 Recommend 0.1 91 ramen 0.15 92 Ramen 0.15 93 lamen 0.15 94 taipeicuisine 0.1

95 🍜 0.15

144 #delicious 0.1 169 #foodheaven 0.1

170 好友 0.1

218 最代表性的餐廳 0.95

290 完美絕配 6

364 份量也蠻夠 1

438 放在清單好久 6 458 LOVEYOU3000 8 459 愛你 3000 8

512 拉肚子 -0.3

586 負評 -0.2

660 裝傻 -0.13

734 最爛 -0.5

808 無法回答 -0.05 822 overrated -0.65

823 滿苦的 -9

880 🐷 0.2

881 ✔ 0.1

882 🎊 0.1

883 🇷 0

884 🇺 0

885 🇸 0

886 💃 0.5

887 🐟 0.1

888 🌊 0.1

889 沒什麼味道 -0.1 890 整個氣勢輸一半 -0.3

891 🍓 0.3

892 還是比較喜歡 -0.1 893 不會回訪 -0.4

894 🔅 0.05

895 略鹹了些 -1

896 ▪ 0.05

897 沒有味道 -0.1

898 比較偏酸 -1

899 融化很快 -1

900 不是我喜歡的 -0.5

901 會比較酸 -3

902 感覺可以再 -0.8 903 如果可以再 -0.6

相關文件