當學校行政人員欲了解某校務事件新聞的輿論效應，其往往透過網際網路搜尋該事件新聞之留言，再瀏覽全部留言後主觀地運用相似留言中之特徵判斷留言的主題，之後再仔細瀏覽各留言並主觀地判斷各留言所隸屬之主題，以取得該校務事件新聞之輿論趨勢，進而協助學校高層官員構思與作出具體決策。然而，現今新聞平台或社群平台均無法自動分析某校務事件新聞所引起之留言的留言主題，以致學校行政人員往往需耗費大量時間閱讀與理解全部留言內容並主觀訂定留言主題及其特徵，再重新閱讀各留言內容以主觀判斷各留言之特徵與各留言主題之特徵的相似度，以將各留言歸屬至對應留言主題，進而了解該校務事件新聞之輿論傾向。
為解決學校行政人員了解留言輿論趨向所面臨之問題，本研究乃先透過前置階段蒐集文教事件新聞所衍生之留言，並整理留言之特徵值、留言主題判斷原則與留言所隸屬之留言主題判斷原則。之後，本研究根據置階段之解析結果，本研究發展一套「留言主題趨向分析」方法論，而此方法論主要包含「留言內容特質擷取」、「留言主題判定」、「留言所隸屬之留言主題判定」與「留言趨向分析」等四大階段。其中，「留言內容特質擷取」階段可將網際網路所蒐集之留言依留言內容擷取特徵點（即可辨識其特質之詞彙）；之後，「留言主題判斷」階段乃依留言內容特質擷取結果比較各留言間之關聯性，以判別留言主題並建立各留言主題所對應之特質；接著，「留言所隸屬之留言主題判斷」階段乃透過比較各留言主題的特質與各留言內容的特質擷取結果之相似度判斷各留言所應隸屬之留言主題；最後，「留言趨向分析」階段則將各留言主題所對應之留言數以視覺化方式呈現，以利讀者快速且準確地判斷所關注之新聞事件所對應之目前輿論趨向。
未來，若學校行政人員欲了解某校務事件新聞之輿論傾向時，即可透過此些事件新聞之留言所對應的留言主題趨向視覺化圖式結果，釐清該校務事件新聞所對應之主題趨向，進而協助學校高層長官快速且準確構思出針對該校務事件新聞的具體對策。

To know the trend of a specific news related to school, staff firstly tend to search for the comments related to the news, then read and analyze all the comments to find the characteristics of comments related to educational news. Secondly, they will review all the comments to shape the topics and categorized all the comments into the above topics. However, there are two problems exists currently. First of all, current social media platform cannot automatically analyze the trend of comments related to a specific school news. Second, staff need to waste a lot of time reading and juding the topics of comments related to a specific news so as to get the trend of a specific school news.
To solve the above problem, we proposed a preparation stage to figure out the characteristics of comments related to educational news, the principles of generating topics related to comments and the principles of judging the topics of comments. After that, we proposed a Trend Analysis of Comment Topics Methodology, it includes four stages, which are collecting comment characteristics, judging comment topics, judging the topic of each comment, analyzing comment trend. As for collecting comment characteristics stage, it can collect the six characteristics of each comment. As for judging comment topics stage, it can compare the relationship among all the comments. As for judging the topic of each comment stage, it can categorize each comment into its topic. As for analyzing comment trend stage, it can show the graph of comment topics. This methodology we proposed can assist user to get the trend of a specific news related to school fastly and accurately.
In the future, we hope the methodology and system we proposed can help staff can use the methodology and the related system to analyze the trend of a specific news, know the trend of a specifc news by the multiple graph related to the topics, make a quick decision in reponse to the specific news related to school.

1. Akaichi, J., 2013, “Social networks’ Facebook’ statutes updates mining for sentiment classification,” Social Computing, Vol. 1, pp. 886-891.
2. Amit, C., Rahul, R. and Savita, A., 2013, “A new approach to detect and extract characts from off-line printed images and text”, Procedia Computer Science, Vol.17, pp. 434-440.
3. Amrutha, B. and Mintu, P., 2015, “Keyword based Tweet extraction and detection of related topics,” Procedia Computer Science, Vol. 46, pp. 364-371.
4. Barnaghi, P., Ghaffari, P. and Breslin, J. G., 2016, “Opinion mining and sentiment polarity on Twitter and correlation between events and sentiment,” IEEE Big Data Computing Service and Applications, pp. 52-57.
5. Barnett, G. A., Xu, W. W., Chu, J., Jiang, K., Huh, C., Park, J. Y. and Park, H. W., 2016, “Measuring international relations in social media conversations,” Government Information Quarterly, pp. 1-8.
6. Bonzanini, M., Martinez-Alvarez, M., and Roelleke, T., 2012, “Opinion summarization through sentence extraction: An investigation with movie reviews,” Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1121-1122.
7. Cai, H. Yang, Y., Li, X. and Huang, Z., 2015, “What are popular: Exploring Twitter features for event detection, tracking and visualization,” Proceedings of the 23rd ACM international conference on Multimedia, pp. 89-98.
8. Chae, J., Thom, D., Bosch, H., Jang, Y., Maciejewski, R., Ebert, D. S. and Ertl, T., 2012, “Spatiotemporal social media analtics for abnormal event detection and examination using seasonal-trend decomposition,” IEEE Symposium on Visual Analytics Science and Technology, pp. 143-152.
9. Chen, S., Yuan, X., Wang, Z. Guo, C., Liang, J., Wang, Z., Zhang, X. and Zhang, J., 2016, “Interactive visual discovering of movement patterns from sparsely sampled geo-tagged social media data,” IEEE Transcation on Visualization and Computer Graphics, Vol. 22, pp. 270-279.
10. Chen, Y. H., Lu, J. L. and Tsai, M. F., 2014, “Finding keywords in blogs: Efficient extraction in blog mining via user bahaviors,” Expert Systems with Applications, Vol. 41, pp. 663-670.
11. Coppersmith, G., Ngo, K., Leary, R. and Wood, A., 2016, “Exploratory analysis of social media prior to a suicide attempt,” Proceedings of the 3rd Workshop on Computational Lingustics and Clinical Psychology: From Lingustic Signal to Clinical Reality, pp. 106-117.
12. Crnovrsanin, T., Muelder, C. W., Faric, R., Felmlee, D. and Ma, K. L., 2014, “Visuzlization techniques for categoriacal analysis of social networks with multiple edge sets,” Social Networks, Vol. 37, pp. 56-64.
13. Croitoru, A., Wayant, N., Crooks, A., Radzikowski, J. and Stefanidis, A., 2014, “Linking cyber and physical spaces through community detection and clustering in social media feeds,” Computers, Environment and Urban Systems, Vol. 53, pp. 47-64.
14. Desai, S. and Patil, S.T., 2015, “Efficient regression algorithms for classification of social media data,” International Conference on Pervasive Computing, pp. 1-5.
15. Elena, L. and Manuel, P., 2013, “Towards automatic Tweet generation: A comparative study from the text summarization perspective in the journalism genre,” Experts Systems with Applications, Vol. 40, pp. 6624-6630.
16. Endarnoto, S. K., Pradipta, S., Nugroho, A. S., and Purnama, J., 2011, “Traffic condition information extraction & visualization from social media Twitter for Andoris mobile application,” International Conference on Electrical Engineering and Informatics, pp. 1-4.
17. Hemant, P., Guozhu, D., Valerie, S., Krishnaprasad, T. and Amit, S., 2015, “Intent classification of short-text on social media,” International Conference on Smart City, pp. 222-228.
18. Hu, M., Wongsuphasawat, K. and Stasko, J., 2017, “Visualizing social media content with senten tree,” IEEE Transcription on Visuzlization and Computer Graphics, Vol. 23, pp. 1-10.
19. Huang, S., Zhang, J., Wang, X. S. Hua, X. S., “Social friend recommendation based on multiple network correlation,” IEEE Transcation on Multimedia, Vol.18, pp. 287-299.
20. Jan, W. V. D. and Michel, V. D. V., 2014, “Online Profiling and clustering of Facebok users,” Decision Support System, Vol. 70, pp. 60-72.
21. Jennifer, G., Cristina, R., Michon, E. and Karen, T., 2011, “Predicting personality from Twitter,” IEEE International Conference on Social Computing, Vol. 1, pp.149-156.
22. Kamel N., 2012, “Ontology-based information extraction from Twitter,” Proceedings of the Workshop on Information Extraction and Entity Analytics on Social Media Data, pp. 17-22.
23. Kang, J. and Lee, H., 2017, “Modeling user interest in social media using news media and wikipedia,” Information System, Vol. 65, pp. 52-64.
24. Kavanaugh A. L., Fox, E. A., Sheetz, S. D., Yang, S., Li, L. T., Shoemaker, D. J., Nastev, A. and Xie, L., 2012, “Social media use by government: From the routine to the critical,” Government Information Quarterly, Vol. 29, pp. 480-491.
25. Li, Z., Zhou, D., Juan, Y. F. and Han, J., 2010, “Key word extraction for social snippets,” Procedding of the 19th International Conference on the World Wide Web, pp. 1143-1144.
26. Lin, C. Y., Li, T. Y. and Chen, P., 2016, “An information visualization system to assist news topics exploration with social media,” Proceeding of 2016 International Conference on Social Media and Society, pp. 23-31.
27. Lipizzi, C., Dessavre, D. G., Iandoli, L. and Marquez, J. E. R., 2016, “Social media conversation monitoring: Visualize information contents of Twitter messages using conversational metrics,” Procedia Computer Science, Vol. 80, pp. 2216-2220.
28. Liu, C. Y., Zhu, C. H., Zhao, T. J. and Zheng, D. Q., 2012, “Extracting main content of a topic on online social network by multi-document summarization,” International Conference on Computer Intelligence and Security, pp. 52-55.
29. Liu, S. and Young, S. D., 2016, “A survey of social media data analysis for physical activity surveillance,” Journal of Forensic Legal Medicine, pp. 1-4.
30. Liu, X. H., Yan, X., Yu, Z. T., Qin, G. S. and Mo, Y. Y., 2015, “Keyword extraction for Web news documents based on LM-BP neural network,” 2015 27th Chinese Control and Decision Conference, pp. 2525-2531.
31. Miao, F., Qiang, Z. and Thomas, F. Z., 2014, “Mining the personal interests of microbloggers via exploiting Wikipedia knowledge,” Computation Linguistics and Intelligent Text Processing, Vol. 8404, pp. 188-200.
32. Muhammad, I., Shady, E., Carlos, C., Fernando, D. and Patrick, M., 2013, “Extraction information nuggets from disaster-related messages in social media,” Procedding of the 10th ISCRAM Conference, pp.1-10.
33. Nicholas D., Mor N. and Funda K.S., 2010, “Diamonds in the rough: Social media visual analytics for journalistic inquiry,” Analytics Science and Technology, Vol. 29, pp. 115-122.
34. Phat, J., Virach, S., Okumura, M. and Choochart, H., 2015, “Effectiveness of social media text classification by utilizing the online news category,” Advanced Informatics: Concepts, Theory and Applications, pp. 1-5.
35. Qing, P. and Christopher, C. Y. and Sarah A. M., 2016, “Breast cancer symptom clusters derived from social media and research study data using improved K-Medoid clustering,” IEEE Transactions on Computational Social Systems, pp. 63-74.
36. Rao, V. P., Galande, S., Nalla, A., Devghare, S. and Kadam, S., 2016, “Visualization of streaming data using social media,” Imperial Journal of Interdisplinary Research, Vol. 2, pp. 602-605.
37. Ratkiewicz, J., Conover, M. D., Meiss, M. Goncalves, B., Flammini, A.and Menczer, F., 2011, “Detecting and tracking political abuse in social media,” International AAAI Conference on Weblogs and Social Media, pp. 297-304.
38. Shabina, D., Harmunish, T. and Kavita, T., 2016, “NLP and ontology based clustering – An integrated approach for optimal information extraction from social Web,” International Conference on Computing for Sustainable Global Development, pp. 1765-1770.
39. Singh, V. K., Waila, P., Piryani, R. and Uddin, A., 2013, “Computational exploration of theme-based blog data using topic modeling, NERC and sentiment classifier combine,” AASRI Conference on Intelligent Systems and Control, pp. 212-222.
40. Supatta, V., Parinya, S., Pisit, C. and Choochart, H., 2015, “A comparison of similarity measures for online social media thai text classification,” Electrical Engineering / Electronic, Computer, Telecommunications and Information Technology (ECTI-CON), 2015 12th International Conference on, pp. 1-6.
41. Suzanne, A., Paulo, D. and Carla, H., 2016, “Travelers’ use of social media: A clustering approach,” Annals of Tourism Research, Vol. 59, pp. 1-15.
42. Takamu, K. and Keiji, Y., 2015, “Event photo mining from Twitter using keyword bursts and image clustering,” Neurocomputing, Vol. 172, pp. 143-158.
43. Timo, R. and Philipp, C., 2012, “Event-based classification of social media streams,” 2016 Symposium on Colossal Data Analysis and Networking (CDAN), pp. 22-29.
44. Uchida, Y., Yoshikawa, T., Furuhashi, T., Hirao, E. and Iguchi, H., 2009, “Extraction of important keywords in free text of questionnaire data and visualization of relationship among sentences,” Fuzzy Systems, pp. 1604-1608.
45. Vidhyabhushan, D., Milap, P. and Narendra, P. S. R., 2016, “An implementation of graph based text classification technique for social media,” 2016 Symposium on Colossal Data Analysis and Networking (CDAN), pp. 1-7.Yu, W., Li, H., Pan, N. and Liu, Z., 2016, “Social media user participation based on ensemble clustering,” Service Systems and Service Management, pp. 1-6.
46. Wang, T., 2017, “Socail identity dimensions and consumer behavior in social media,” Asia Pacific Management Review, pp. 1-7.
47. Wen, C. Teng, Z., Chen, J., Wu, Y., Gong, R. and Pu, J., 2016, “Socialradius: visual exploration of user check-in behavior based on social media data,” International Conference on Cooperative Design Visualization and Engineering, pp. 300-308.
48. Williams, E., Gray, J., Morris, E., Bradshaw, B., Williams, K. and Brandon, D., 2016, “A comparison of two methods for the topical clustering of social mediaposts,” Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 1-7.
49. Wu, Y., Cao, N., Gotz, D., Tan, Y. P. and Keim, A., 2016, “A survey on visual analytics of social media data,” IEEE Transcations on Mutimedia, Vol.18, pp. 2135-2148.
50. Xia, C., Schwartz, R., Xie, K., Krebs, A., Langdon, A., Ting, J. and Naaman, M., 2014, “Citybeat: Real-time social media visualization of hyper-local city data,” Proceedings of the 23rd International Conference on World Wide Web, pp. 167-170.
51. Xiang, Z., Du, Q., Ma, Y. and Fan, W., 2017, “A comparative analysis of major online review platforms: Implications for social media analytics in hospitality abd tourism,” Tourism Management, Vol. 58, pp. 51-65.
52. Xu, P. Wu, Y., Wei, E., Peng, T. Q., Liu, S., Zhu, J. J. H. and Qu, H., 2013, “Visual analysis of topic competition on social media,” IEEE Transcation on Visualization and Computer Graphics, Vol. 19, pp. 2012-2021.
53. Yu, W., Li, H., Pan, N. and Liu, Z., 2016, “Social media user participation based on ensemble clustering,” Service Systems and Service Management, pp. 1-6.
54. Zhao, S., Zhong, L., Wickramasuriya, J. and Vasudevan, V., 2011, “Analyzing Twitter for social TV: Sentiment extraction for sports,” Proceedings of the 2nd International Workshop on Future of Television, Vol. 2, pp. 11-18.
55. Zhiqi, F., Yue, N. and Tingshao Z., 2010, “Hot keyword identification for extracting web public opinion,” IEEE 5th International Conference on Pervasive Computing and Applications, pp. 116-121.
56. Zingla, M. A., Chiraz, L., Slimani, Y. and Berrut, C., 2015, “Statistical and semantic approaches for Tweet contextualization,” Procedia Computer Science, Vol. 60, pp. 498-507.