千百年來，與宗教相關的議題總是熱度不減。隨著網路時代的來臨，社群網路的興起，更是將宗教話題推向了公眾視野。與此同時，更是有許多不和諧的現象與事件在社群網路上被歸結于宗教原因，致使宗教被蒙上了一層陰影，令社會大眾心存疑慮。宗教為何？它對人們的影響究竟為何？這個疑問似乎越來越難以得到解答。再次挑戰來臨之際亦是機遇降臨之時。本研究充分利用社群網路所提供的海量資料基礎，收集超過2000萬份來自與宗教相關的Twitter用戶包含佛教、伊斯蘭教、天主教之英文推文，區域多樣性涵蓋英國、加拿大和美國的15個以上地區，通過情緒分析的實驗方式探尋出宗教可能對其受眾的情緒分佈產生的影響，使從前抽象的概念得到視覺化的直觀體現。此項研究在宏觀的基礎上再由表及內的進行深化探究，運用概念導向性分析，將研究點具體到特定事項，來探索宗教對其受眾在具體領域上情緒分佈所產生的影響。

Just as religion has an impact on human beings and their society, the exploration of religious influence on human also has never stopped. It is easier to find a few clues from a glimpse of people's physical daily life discovering the external manifestation of the influence of religion on its audience; however, discovering the influence of religion on their mental layer has always been a challenge so far. This research will introduce a methodology that explores the impact of religion on people from an emotion analyzing perspective, and such emotions will include disgust, anticipation, joy, surprise, sadness, fear and anger. More than 20 million English based tweets were collected from over 15 districts across the United Kingdom, Canada, and the United States. Such text data were processed to run into a visualized results letting the public know the influence that religion would have on emotion distribution of religion's audience. This research is going to compare religion-related emotion distribution by workday and weekend, location factors will also be taken into consideration.

Abstract
Contents
Introduction--------------------------------------------------1
Related work--------------------------------------------------4
Methodology---------------------------------------------------9
OverView of representative emotion Distribution--------------21
Concept-based Results Analysis and Explanations--------------51
Conclusion and future works----------------------------------62
Reference----------------------------------------------------64

[1] GENEIVE ABDO. Like most Americans, u.s. muslims concerned about extremism in the name of Islam. volume Fact Tank.
[2] Carlos Argueta, Fernando H Calderon, and Yi-Shin Chen. Multilingual emotion classifier using unsupervised pattern extraction from microblog data.Intelligent data analysis, 20(6):1477–1502, 2016.
[3] A Ben Ze’ev. The subtlety of the emotion.Cambridge University Press, 2002.
[4] Pew Research Center. Being Christian in western Europe. volume Religion PublicLife.
[5] Elvis Saravia — Hsien-Chi Toby Liu — Yen-Hao Huang — Junlin Wu — Yi-ShinChen. Carer: Contextualized affect representations for emotion recognition.Empirical Methods in Natural Language Processing, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing:3687–3697, 2018.
[6] Akshi Kumar ; Prakhar Dogra ; Vikrant Dabas. Emotion analysis of twitter using opinion mining. In2015 Eighth International Conference on Contemporary Comput-ing (IC3), pages 285–290. IEEE, 2015.64
[7] Dmitry Davidov, Oren Tsur, and Ari Rappoport. Enhanced sentiment learning using twitter hashtags and smileys. InProceedings of the 23rd international conference on computational linguistics: posters, pages 241–249. Association for ComputationalLinguistics, 2010.
[8] Alec Go, Richa Bhayani, and Lei Huang. Twitter sentiment classification using distant supervision.CS224N Project Report, Stanford, 1(2009):12, 2009.
[9] Xia Hu, Jiliang Tang, Huiji Gao, and Huan Liu. Unsupervised sentiment analysis with emotional signals. InProceedings of the 22nd international conference on World wide web, pages 607–618. ACM, 2013.
[10] Osvaldo N. Oliveira Jr Diego R. Amancio-Leticia L. Mansur Sandra M. Alusio Le-andro B. dos Santos, Edilson A. Correa Jr. Enriching complex networks with word embeddings for detecting mild cognitive impairment from speech transcripts. Association for Computational Linguistics, pages 1284–1296, 2017.
[11] R.N McCauley. Religion in mind: Cognitive perspectives in religion belief, ritual, and experience. InRitual, memory and emotion: Comparing two cognitive hypotheses.
[12] SerkanAyvaz Nazanztrk. Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis.Telematics and Informatics, 35:136–147, 2018.
[13] Alvaro Ortigosa, Jos ́e M Mart ́ın, and Rosa M Carro. Sentiment analysis in Facebook and its application to e-learning.Computers in Human Behavior, 31:527–541, 2014.
[14] Robert Plutchik. Emotion: Theory, research, and experience: Theories of emotion.Academic, 1(1), 1980.65
[15] Yi-Shin Chen Po-Chen Kuo. Automatic sarcasm detection through emotion reactions on social media platforms. 2017.
[16] P.W Pruyser. A dynamic psychology of religion.Harper Row, 1967.
[17] Francisco Rangel and Paolo Rosso. On the identification of emotions and authors gender in Facebook comments on the basis of their writing style. pages 4–6, 2013.
[18] Mutua Kobia Semegnish Asfaw. Freedom of religion and belief–public statements and issues of the commission of the churches on international affairs. 7, number=,pages=, year=2017, publisher=World Council of Churches.
[19] Duyu Tang, Bing Qin, Ting Liu, and Zhenghua Li. Learning sentence representation for emotion classification on microblogs. natural Language Processing and Chinese Computing, pages 212–223. Springer, 2013.
[20] Wenbo Wang, Lu Chen, Krishnaprasad Thirunarayan, and Amit P Sheth. Harnessingtwitter” big data” for automatic emotion identification. InPrivacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom), pages 587–592. IEEE, 2012.
[21] Yaowei Wang, Yanghui Rao, Xueying Zhan, Huijun Chen, Maoquan Luo, and JianYin. Sentiment and emotion classification over noisy labels.Knowledge-Based Systems, 111:207–216, 2016.
[22] Jichang Zhao, Li Dong, Junjie Wu, and Ke Xu. Moodlens: an emoticon-based sentiment analysis system for Chinese tweets. InProceedings of the 18th ACM SIGKDD66
international conference on Knowledge discovery and data mining, pages 1528–1531.ACM, 2012