跳到主要內容

臺灣博碩士論文加值系統

(44.211.31.134) 您好!臺灣時間:2024/07/23 06:21
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:連育正
研究生(外文):Yu-Cheng Norm Lien
論文名稱:循序樣型探勘在引導使用者解決問題和主題分類的機器學習在社群媒體內容分析的方法
論文名稱(外文):Methods of Sequential Pattern Analysis for Guiding Learning Problem-Solving and Machine-Learning Thematic Classification for Social-Media Content Analysis
指導教授:吳文中
指導教授(外文):Wen-Jong Wu
口試委員:李世光張瑞益林致廷梁文耀
口試委員(外文):Chih-Kung LeeRay-I ChangChih-Ting LinWilliam Liang
口試日期:2021-10-20
學位類別:博士
校院名稱:國立臺灣大學
系所名稱:工程科學及海洋工程學研究所
學門:工程學門
學類:綜合工程學類
論文種類:學術論文
論文出版年:2021
畢業學年度:109
語文別:英文
論文頁數:101
中文關鍵詞:數據探勘不明確的問題機器預測問題解決序列模式探勘教師效能流行病嚴重程度COVID-19公共衛生當局外展公共參與社會情緒機器學習主題分類
外文關鍵詞:data miningill-defined problemmachine predictionproblem-solvingsequential pattern miningteacher effectivenessepidemic severityCOVID-19public health authorityoutreachpublic engagementsocial sentimentmachine learningthematic classification
DOI:10.6342/NTU202104101
相關次數:
  • 被引用被引用:0
  • 點閱點閱:51
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
機器學習(Machine Learning)在預測人類個體行為或了解社會群體意志的潛力與價值,愈來愈受到重視。基於此,本論文包含兩項運用機器學習的研究,一是運用序列模式探勘(sequence pattern mining)以解決如何引導學習者進入正確學習路徑的問題;另一是使用監督式機器學習(supervised machine learning)進行 Facebook 內容分析,發掘在 COVID-19 時代的公共衛生當局的外展、公眾參與和社會情緒等議題和圖像。茲分述如下。

研究一主題:在解決 STEM 教育中定義不明確的問題時,教師如何預測學生的行為:使用序列模式挖掘的解決方案
預測學習者在解決問題行為過程的動線,有助於為學習者(學生)提供足夠的指導,但這仍然是科學、技術、工程和數學 (STEM) 教育中的一個艱難挑戰。鑑於目前新興的數據挖掘技術大幅發展,但尚缺乏相關研究能用以支持指導者(教師)來有效預測學生面對不明確問題 (ill-defined problem, IDP) 時的處理程序,因此本研究旨在通過測量指導者和機器預測的相對品質來填補當今研究的不足,以做為未來利用專家系統指導學生學習STEM的基礎。本研究以 43 名小學教師在本研究設計的光路任務 (the light path task, LPT) 預測學習者在解決 IDP 時的逐步行動,然後將其預測品質與序列模式挖掘技術執行的機器預測的質量進行比較。從 501 名 11-12 歲的 5 年級和 6 年級學習者中收集了有關學習者行動方針的數據。結果表明,與機器預測相比,專家預測的準確率明顯較低,這突出了使用數據挖掘預測學習者行為的優勢,並顯示了其作為推薦系統在未來 STEM 教育中提供自適應指導的潛力和可能應用。

研究二主題:使用機器學習的 Facebook 內容分析:台灣、新加坡、美國和英國在 COVID-19 的前疫苗階段之疫情嚴重程度、公共衛生當局的外展、公眾參與和社會情緒
社交媒體對於傳播信息和影響公眾輿論至關重要,尤其是在面臨像是 2019 年的新冠狀病毒 (COVID-19) 這種前所未有對社會和人類的威脅時。政府將社交媒體用於外展(outreach)、公眾參與(public engagement)和社會情緒(social sentiment),不僅反映了公眾對政府的滿意度,還展示了對抗疾病的意識和努力。然而,由於先前的研究所採用的數據侷限在較短的時期和大量的評論無法以由人工分析的限制,許多重要信息因之流失,而突顯了進一步研究的必要性。本研究旨在探討公共衛生當局 (public health authorities, PHA) 的外展、公眾參與和社會情緒。本研究將比較PHAs的Facebook (FB) 貼文 (posts) 數量以代表其外展工作方面的努力,還比較其追隨者 (followers) 的評論 (comments),展示4個選擇研究對象:台灣、新加坡、美國和英國 (selected-four; S4) 的公眾參與和社會情緒之間的差異。研究並以機器學習進行主題歸類 (thematic classification),以解決舊有社會情意分析敏感性不足的問題。本研究對4個PHA官方FB頁面進行分析,提取2020年1月1日至2021年1月31日期間的3787條貼文和665,298條評論進行分析。使用自動機器情感分析獲得評論的情感極性 (sentiment polarity),並開發了一種機器學習方法,將評論分為六個主題。所獲得數據運用獨立樣本 Kruskal-Wallis檢定並採 Dunn-Bonferroni 事後檢驗分析。相關統計結果並和其確診病例數對照比較,以觀察疫情嚴重程度與社會情緒的關聯。
研究結果發現,研究中探討的各項主要變因均發現顯著差異。對於PHAs的外展努力部分,美國 > 新加坡和英國 (P = 0.009;P < 0.001),以及台灣 > 英國 (P < 0.001);對於公眾參與,新加坡和台灣 > 美國和英國 (分別為 P = 0.020 和 0.000,以及 P = 0.020 和 0.001);對於社會情緒,新加坡 > 美國和英國 (分別為 P < 0.001 和 P < 0.000)和台灣 > 英國 (P = 0.012)。此外,本研究發展的機器學習分類,表現出令人滿意的表現 (例如,真陽性 = 0.75)。採用此方法,進一步的主題分析下揭示了各主題中,S4 之間的公眾參與和社會情緒的顯著差異。在疫情嚴重程度方面,台灣最輕 (P < 0.002);不過卻發現,雖然新加坡的疫情嚴重程度較西方國家稍輕或相近,但在各個主題方面的社會情緒均明顯較為正面。這項研究揭示了公眾參與和社會情緒與疫情嚴重程度的關聯,此在之前的研究中並未獲得充分探討。本研究也深入探析 PHAs 的外展、公眾參與、社會情緒和流行病嚴重程度方面的一些差異,揭示了嚴重疫情期間不同社會的不同反應。最終,這項研究提出了其他 PHAs 可以用來分析外展工作和追隨者評論的影響的方法,能更有效的監測和調整健康保護措施和了解公眾的參與與社會情緒。
Machine learning has been paid more and more attention to the potential and value of predicting individual human behaviors or understanding public opinions. Based on this, this work contains two studies adopting machine learning techniques: one is the use of sequence pattern mining to solve the problem of how to guide learners into the correct learning path; the other is the use of supervised machine learning techniques for Facebook content analysis to discover issues and images of public health authorities’ outreach, public engagement, and social sentiment in the COVID-19 era. The details are as follows:

Study 1: How Well Do Teachers Predict Students’ Actions in Solving an Ill-Defined Problem in STEM education: A Solution Using Sequential Pattern Mining
Predicting students’ line of actions helps educators give adequate guidance to students, but this remains a challenge in science, technology, engineering, and mathematics (STEM) education. Given this, there is a scarcity of related research that will help improve teachers’ prediction capabilities on students’ line of actions when tackling ill-defined problems (IDPs), as well as how emerging data mining techniques could contribute to such prediction. The present study aims to fill the gap by measuring the quality of teachers’ predictions (labeled expert prediction), where 43 elementary teachers predict students’ step-by-step actions when solving an IDP through the light path task (LPT), and then comparing its quality with that of machine prediction, executed via sequential pattern mining techniques. Data on students’ lines of action were collected from 501 5th- and 6th-grade students, aged 11–12. The results showed the significantly lower accuracy of expert prediction compared to machine prediction, which highlights the advantages of using data mining in predicting students’ actions and shows its possible application as a recommendation system to provide adaptive guidance in future STEM education.

Study 2: Facebook Content Analysis Using Machine Learning: Public Health Authorities’ Outreach, Public Engagement, and Social Sentiment Considering Epidemic Severity amid pre-vaccination COVID-19 Era in Taiwan, Singapore, US, and UK (S4)
Background: Social media is essential for disseminating information and influencing public opinion, particularly when facing unprecedented threats such as the coronavirus disease 2019 (COVID-19) before vaccines widely availed. Governments’ social media use for outreach, public engagement, and social sentiment not only reflects public satisfaction toward administrations but also demonstrates disease awareness and efforts. However, with limited time for data selection and online comments unsuitable for manual analysis in previous studies, vast amounts of information were unaccounted for, highlighting the need for further scrutiny. Objective: This study aims to identify public health authorities (PHAs)’ outreach, public engagement, and social sentiment with and without thematic classification; compare not only the number of PHAs’ Facebook (FB) posts on outreach efforts but also followers’ comments to demonstrate differences between public engagement and social sentiment in Taiwan, Singapore, the United States, and the United Kingdom (S4) through comments’ thematic classification; and show how epidemic severity affects social sentiment amid the pre-vaccination COVID-19 era. Methods: Four PHAs’ official FB pages were analyzed, wherein 3,787 posts and 665,298 comments made between January 1, 2020, and January 31, 2021, were extracted for analysis. Comments’ sentiment polarity was obtained using automatic machine sentiment analysis, and a machine learning method was developed, classifying comments into six themes. Numbers were arranged by month before applying independent-sample Kruskal-Wallis and Dunn-Bonferroni post hoc tests. The number of confirmed cases was also identified to represent epidemic severity and observe its association with social sentiments. Results: Significant differences were found for each factor: for outreach, United States > Singapore and United Kingdom (P = 0.009; P < 0.001), and Taiwan > United Kingdom (P < 0.001); for public engagement, Singapore and Taiwan > United States and United Kingdom (P = 0.020 and 0.000, and P = 0.020 and 0.001, respectively); and for social sentiment, Singapore > United States and United Kingdom (P < 0.001 and P < 0.000, respectively) and Taiwan > United Kingdom (P = 0.012). Machine learning classification showed satisfactory performance (e.g., true positive = 0.75), and further thematic analyses revealed significant differences in public engagement and social sentiment across both themes and S4. In terms of epidemic severity, Taiwan experienced the lightest (P < 0.002), while Singapore had lighter or similar epidemic severity than the Western countries yet showed significantly higher social sentiment in each thematic aspect. Conclusions: This study unveiled the association of public engagement and social sentiment with epidemic severity, which was insufficiently explored in previous studies. Several differences in PHAs’ outreach, public engagement, social sentiment, and epidemic severity were identified, revealing varying reactions across different societies amid the pandemic. Ultimately, this study presented implications and methods other PHAs could use in analyzing outreach efforts and followers’ comments to monitor and adjust protective measures and public engagement.
Table of Contents
謝辭 i
Abstract v
Table of Contents vii
List of Figures viii
List of Tables x
Study 1: How Well Do Teachers Predict Students’ Actions in Solving an Ill-Defined Problem in STEM education: A Solution Using Sequential Pattern Mining 1
Introduction 3
Theoretical Background 5
Research Methods 11
Results and Discussion 21
Conclusion 27
References 29
Study 2: Facebook Content Analysis Using Machine Learning: Public Health Authorities’ Outreach, Public Engagement, and Social Sentiment Considering Epidemic Severity amid Pre-vaccination COVID-19 Era in Taiwan, Singapore, US, and UK (S4) 33
Introduction 35
Methods 45
Results 53
Discussion 83
Conclusions 89
Appendix 1. Commands and Parameters of Selected Classifiers 95
References 97
Study 1:
1. R. Duschl, S. Maeng, and A. Sezen, “Learning progressions and teaching sequences: a review and analysis,” Stud. Sci. Educ., vol. 47, no. 2, pp. 123–182, Sep. 2011.
2. J. K. Gilbert, R. J. Osborne, and P. J. Fensham, “Children’s science and its consequences for teaching,” Sci. Educ., vol. 66, no. 4, pp. 623–633, Jul. 1982.
3. T. Barnhart and E. van Es, “Studying teacher noticing: Examining the relationship among pre-service science teachers’ ability to attend, analyze and respond to student thinking,” Teach. Teach. Educ., vol. 45, pp. 83–93, Jan. 2015.
4. S. D. Nickerson, L. Lamb, and R. LaRochelle, “Challenges in measuring secondary mathematics teachers’ professional noticing of students’ mathematical thinking,” in Teacher Noticing: Bridging and Broadening Perspectives, Contexts, and Frameworks, E.O. Schack, M.H. Fisher, and J.A. Wilhelm, Eds. NY, USA: Springer, Cham, 2017, pp. 381–398.
5. C. Lynch, K. Ashley, V. Aleven, and N. Pinkwart. (2006, Jan.). Defining “ill-defined domains”; A literature survey. Presented at the ITS ’06. [Online]. Available: https://people.engr.ncsu.edu/cflynch/Papers/ITS06_illdefinedworkshop_LynchEtAl.pdf
6. National Research Council, Learning to Think Spatially. Washington, DC, USA: NAP, 2006.
7. N. T. Le, F. Loll, and N. Pinkwart, “Operationalizing the continuum between well-defined and ill-defined problems for educational technology,” IEEE Trans. Learn. Technol., vol. 6, no.3, pp. 258–270, Apr. 2013.
8. P. Wright, A. T. Wright, A. B. McCoy, and D. F. Sittig, “The use of sequential pattern mining to predict next prescribed medications,” J. Biomed. Inform., vol. 53, pp. 73–80, Feb. 2015.
9. R. S. Baker and K. Yacef, “The state of educational data mining in 2009: A review and future visions,” JEDM, vol. 1, no. 1, pp. 3–17, Oct. 2009.
10. B. Bakhshinategh, O. R. Zaiane, S. ElAtia, and D. Ipperciel, “Educational data mining applications and tasks: A survey of the last 10 years,” Educ. Inform. Tech., vol. 23, no. 1, pp. 537–553, Jan. 2018.
11. Z. Papamitsiou and A. A. Economides, “Learning analytics and educational data mining in practice: A systematic literature review of 30 empirical evidence,” Educ. Technol. Soc., vol. 17, no. 4, pp. 49–64, Oct. 2014.
12. E. Sung and T. R. Kelley, “Identifying design process patterns: A sequential analysis study of design thinking,” Int. J. Technol. Des. Educ., vol. 29, no. 2, pp. 283–302, Mar. 2019.
13. C. Y. Cheng, “A theory of learning (學) in Confucian perspective,” Educ. Philos. Theory, vol. 48, no. 1, pp. 52–63, Jan. 2016.
14. C. A. Sensibaugh, N. J, Madrid, H.-J. Choi, W. L. Anderson, and M. P. Osgood, “Undergraduate performance in solving ill-defined biochemistry problems,” CBE Life Sci. Educ., vol. 16, no. 4:ar63, pp. 1–14, Dec. 2017.
15. J. Wai, D. Lubinski, and C. P. Benbow, “Spatial ability for STEM domains: Aligning over 50 years of cumulative psychological knowledge solidifies its importance,” J. Educ. Psychol., vol. 101, no.4, pp. 817–835, 2009.
16. M. G. Jones, G. Gardner, A. R. Taylor, et al., “Conceptualizing magnification and scale: The roles of spatial visualization and logical thinking,” Res. Sci. Educ., vol. 41, no. 3, pp. 357–368, May 2011.
17. R. Ekstrom, J. French, H. Harman, and D. Dermen, Manual for Kit of Factor-referenced Cognitive Tests. Princeton, NJ, USA: ETS, 1976.
18. T. H. Wang, “Developing web-based assessment strategies for facilitating junior high school students to perform self-regulated learning in an e-learning environment,” Comput. Educ., vol. 57, no. 2, pp. 1801–1812, Sep. 2011.
19. S. Zajac, M. E. Gregory, W. L. Bedwell, W. S. Kramer, and E. Salas, “The cognitive underpinnings of adaptive team performance in ill-defined task situations: A closer look at team cognition,” Organ. Psychol. Rev., vol. 4, no. 1, pp. 49–73, Feb. 2014.
20. F. Tehrani and D. Ahrens, “Modified sequential k-means clustering by utilizing response: A case study for fashion products,” Expert Syst., vol. 34, no. 6, Jul. 2017.
21. P. Fournier-Viger, R. Nkambou, and E. Mephu. (2009, Jul.). Exploiting partial problem spaces learned from users’ interactions to provide key tutoring services in procedural and ill-defined domains. Presented at AIED 2009 Conference. [Online]. Available: https://dl.acm.org/doi/10.5555/1659450.1659509
22. J. K. Febrer-Hernandez and J. Hernandez-Palancar, “Sequential pattern mining algorithms review,” Intell. Data Anal., vol. 16, no. 3, pp. 451–466, May 2012.
23. P. Fournier, J. C. W. Lin, B. Vo, T. T. Chi, J. Zhang, and H. B. Le, “A survey of itemset mining,” WIRES Data Min. Knowl., vol. 7, no. 4, pp. 1–18, Apr. 2017.
24. Waikato Environment for Knowledge Analysis, “WEKA: The workbench for machine learning.” http://www.cs.waikato.ac.nz/ml/weka/ (accessed Dec. 20, 2019).
25. H. Y. Wang, H. B. L. Duh, N. Li, T. J. Lin, and C. C. Tsai, “An investigation of university students’ collaborative inquiry learning behaviors in an augmented reality simulation and a traditional simulation,” J. Sci. Educ. Technol., vol. 23, no. 5, pp. 682–691, Oct. 2014.
26. R. Bakeman and J. M. Gottman, Observing Interaction: An Introduction to Sequential Analysis. Cambridge, UK: CUP, 1997.
27. S. Kucuk and B. Sisman, “Behavioral patterns of elementary students and teachers in one-to-one robotics instruction,” Comput. Educ., vol. 111, pp. 31–43, Aug. 2017.
28. J. S. Kinnebrew, K. M. Loretz, and G. Biswas, “A contextualized, differential sequence mining method to derive students’ learning behavior patterns,” JEDM, vol. 5, no. 1, pp. 190–219, May 2013.
29. C. J. Chang, M. H. Chang, B. C. Chiu, C. C. Liu, S. H. F. Chiang, C. T. Wen, et al., “An analysis of student collaborative problem solving activities mediated by collaborative simulations,” Comput. Educ., vol. 114, pp. 222–235, Nov. 2017.
30. D. Perera, J. Kay, I. Koprinska, K. Yacef, and O. R. Zaiane, “Clustering and sequential pattern mining of online collaborative learning data,” IEEE Trans. Knowl. Data Eng., vol. 21, no. 6, pp. 759–772, Jun. 2009.
31. C. H. Chiu and C. L. Lin, “Sequential pattern analysis: Method and application in exploring how students develop concept maps,” Turkish J. Educational Tech., vol. 11, no. 1, pp. 145–153, Jan. 2012.
32. Grosfeld-Nir, B. Ronen, and N. Kozlovsky, “The Pareto managerial principle: When does it apply?” Int. J. Prod. Res., vol. 45, no. 10, pp. 2317–2325, Apr. 2007.
33. P. Fournier-Viger, C. W. Wu, V. S. Tseng, L. Cao, and R. Nkambou, “Mining partially-ordered sequential rules common to multiple sequences,” IEEE Trans. Knowl. Data Eng., vol. 27, no. 8, pp. 2203–2216, Feb. 2015.
34. M. Salehi and I. N. Kamalabadi, “Hybrid recommendation approach for learning material based on sequential pattern of the accessed material and the learner’s preference tree,” Knowl. Based Syst., vol. 48, pp. 57–69, Aug. 2013.
35. S. J. Yen, Y. C. Wu, J. C. Yang, Y. S. Lee, C. J. Lee, and J. J. Liu, “A support vector machine-based context-ranking model for question answering,” Inform. Sciences, vol. 224, pp. 77–87, Mar. 2013.
36. C. O. Fritz, P. E. Morris, and J. J. Richler, “Effect size estimates: Current use, calculations, and interpretation,” J. Exp. Psychol. Gen.,vol. 141, no. 1, pp. 2–18, 2012.
37. H. Otsuji, P. S. Oh, C. C. Lin, W. M. W. So, and Y.-L. Lu, “Primary school science teacher training in East-Asia: In the continuous reforming for the quality assurance,” in Science Education Research and Practice in East Asia: Trends and Perspectives, H.-S. Lin, J. K. Gilbert, and C.-J. Lien, Eds. Taipei, Taiwan: Higher Education Publishing Co., Ltd., 2016, pp. 245–272.Anon. Details omitted for double-blind review, 2016b.
38. Y.-L. Lu and C.-J. Lien, “Elementary science education in Taiwan—From the perspective of international comparison,” in Science Education Research and Practices in Taiwan: Challenges and Opportunities, M.-H. Chiu, Ed. Singapore: Springer, 2016, pp. 163–180.
39. C. T. Wen, C. J. Chang, M. H. Chang, S. H. F. Chiang, C. C. Liu, F. K. Hwang, and C.C. Tsai. “The learning analytics of model-based learning facilitated by a problem-solving simulation game,” Instr. Sci., vol. 46, no. 6, pp. 847–867, Jun. 2018.
40. Programme for International Student Assessment. (2015). Try PISA 2015 Test Questions. [Online]. Available: www.oecd.org/pisa/test/pisa2015/#d.en.53724. Accessed on: Jan. 22, 2020.
41. PhET Interactive Simulations, “Interactive simulations for science and math.” http://phet.colorado.edu (accessed Jun. 1, 2020).
42. D. Ausubel, Educational Psychology: A Cognitive View. New York, NY, USA: HRW, 1968.
43. L. S. Vygotsky, Mind in Society: The Development of Higher Psychological Processes. Cambridge, MA, USA: HUP, 1978.
44. C. Chand, A. Thakkar, and A. Ganatra, “Sequential pattern mining: Survey and current research challenges,” Int. J. Soft Comput. Eng., vol. 2, no. 1, pp. 185–193, Mar. 2012.
45. G. Z. Bakirli and D. Birant, “DTreeSim: A new approach to compute decision tree similarity using re-mining,” Turk. J. Elec. Eng. & Comp. Sci., vol. 25, no. 1, pp. 108–125, Jan. 2017.
46. C. Gonzalez, P. Fakhari, and J. Busemeyer, “Dynamic decision making: Learning processes and new research directions,” Hum. Factors, vol. 59, no. 5, pp. 713–721, Aug. 2017.
Study 2:
1. World Health Organization. WHO coronavirus (COVID-19) dashboard. Accessed April 2, 2021. https://covid19.who.int/info/
2. Ministry of Health and Welfare, Taiwan. Crucial policies for combating Covid-19. Ministry of Health and Welfare. Accessed April 2, 2021. https://covid19.mohw.gov.tw/ch/sp-timeline0-205.html
3. World Health Organization. Pneumonia of unknown cause – China. Accessed March 20, 2020. https://www.who.int/csr/don/05-january-2020-pneumonia-of-unkown-cause-china/en/
4. National Center for High-performance Computing. Status report of Covid-19 in Taiwan. Accessed March 10, 2021. https://covid-19.nchc.org.tw/dt_005-covidTable_taiwan.php
5. Wang PW, Lu WH, Ko NY, et al. COVID-19-related information sources and the relationship with confidence in people coping with COVID-19: Facebook survey study in Taiwan. J Med Internet Res. 2020;22(6): e20021. doi: 10.2196/20021.
6. Wang JZ, Zhou Y, Zhang W, Evans R, Zhu C. Concerns expressed by Chinese social media users during the COVID-19 pandemic: content analysis of Sina Weibo microblogging data. J Med Internet Res. 2020:22(11):e22152. doi: 10.2196/22152.
7. Huppertz JW, Otto P. Predicting HCAHPS scores from hospitals’ social media pages: a sentiment analysis. Health Care Manage Rev. 2018;43(4):359–367. doi: 10.1097/HMR.0000000000000154.
8. Abd-Alrazaq A, Alhuwail D, Househ M, Hamdi M, Shah Z. Top concerns of tweeters during the COVID-19 pandemic: infoveillance study. J Med Internet Res. 2020;22(4):e19016. doi: 10.2196/19016.
9. Boon-Itt S, Skunkan Y. Public perception of the COVID-19 pandemic on Twitter: sentiment analysis and topic modeling study. JMIR Public Health Surveill. 2020;6(4):245–261. doi: 10.2196/21978.
10. Raamkumar AS, Tan SG, Wee HL. Measuring the outreach efforts of public health authorities and the public response on Facebook during the COVID-19 pandemic in early 2020: cross-country comparison. J Med Internet Res. 2020;22(5). doi: 10.2196/19334.
11. Arora A, Bansal S, Kandpal C, Aswani R, Dwivedi Y. Measuring social media influencer index- insights from facebook, Twitter and Instagram. J Retail Consum Serv. 2019;49:86–101. doi: 10.1016/j.jretconser.2019.03.012.
12. Taleqani AR, Hough J, Nygard KE. Public opinion on dockless bike sharing: a machine learning approach. Transp Res Rec. 2019;2673(4):195–204. doi: 10.1177/0361198119838982.
13. Ghasiya P, Okamura K. Investigating COVID-19 news across four nations: a topic modeling and sentiment analysis approach. IEEE Access. 2021;9:36645–36656. doi: 10.1109/ACCESS.2021.3062875.
14. Kirilenko AP, Stepchenkova SO, Dai XY. Automated topic modeling of tourist reviews: does the Anna Karenina principle apply? Tour Manag. 2021;83:13. doi: 10.1016/j.tourman.2020.104241.
15. Antonakaki D, Fragopoulou P, Ioannidis S. A survey of Twitter research: data model, graph structure, sentiment analysis and attacks? Expert Syst Appl. 2021;164:25. doi: 10.1016/j.eswa.2020.114006.
16. Chan CH, Zeng J, Wessler H, et al. Reproducible extraction of cross-lingual topics (rectr). Commun Methods Meas. 2020;14(4): 285–305. doi: 10.1080/19312458.2020.1812555.
17. Abdul-Rahman M, Chan EHW, Wong MS, Irekponor VE, Abdul-Rahman MO. A framework to simplify pre-processing location-based social media big data for sustainable urban planning and management. Cities. 2021;109:16. doi: 10.1016/j.cities.2020.102986.
18. Khalid M, Ashraf I, Mehmood A, Ullah S, Ahmad M, Choi GS. GBSVM: sentiment classification from unstructured reviews using ensemble classifier. Appl Sci. 2020;10(8):2788. doi: 10.3390/app10082788.
19. Dang NC, Moreno-García MN, De la Prieta F. Sentiment analysis based on deep learning: a comparative study. Electronics. 2020;9(3):29. doi: 10.3390/electronics9030483.
20. Jang HJ, Rempel E, Roth D, Carenini G, Janjua NZ. Tracking COVID-19 discourse on Twitter in North America: infodemiology study using topic modeling and aspect-based sentiment analysis. J Med Internet Res. 2021;23(2):e25431. doi: 10.2196/25431.
21. Lyu JC, Luli GK. Understanding the public discussion about the centers for disease control and prevention during the COVID-19 pandemic using Twitter Data: text mining analysis study. J Med Internet Res. 2021;23(2):e25108. doi: 10.2196/25108.
22. Noor S, Guo Y, Shah SHH, Fournier-Viger P, Nawaz MS. Analysis of public reactions to the novel coronavirus (COVID-19) outbreak on Twitter. Kybernetes. 2020;21. doi: 10.1108/K-05-2020-0258.
23. Desvars-Larrive A, Dervic E, Haug N, et al. A structured open dataset of government interventions in response to COVID-19. Sci Data. 2020;7(1):1–9. doi: 10.1038/s41597-020-00609-9.
24. Sear RF, Velásquez N, Leahy R, et al. Quantifying COVID-19 content in the online health opinion war using machine learning. IEEE Access. 2020;8:91886–91893. doi: 10.1109/ACCESS.2020.2993967.
25. Vijaykumar S, Meurzec RW, Jayasundar K, Pagliari C, Fernandopulle Y. What’s buzzing on your feed? health authorities’ use of Facebook to combat Zika in Singapore. J Am Med Inform Assoc. 2017;24(6):1155–1159. doi: 10.1093/jamia/ocx028.
26. Huang Y, DiStaso M. Responding to a health crisis on Facebook: the effects of response timing and message appeal. Public Relat Rev. 2020;46(3):101909. doi: 10.1016/j.pubrev.2020.101909.
27. Rantanen A, Salminen J, Ginter F, Jansen B. Classifying online corporate reputation with machine learning: a study in the banking domain. Internet Res. 2020;30(1):45–66. doi: 10.1108/INTR-07-2018-0318.
28. Fatima I, Mukhtar H, Ahmad HF, Rajpoot K. Analysis of user-generated content from online social communities to characterise and predict depression degree. J Inf Sci. 2018;44(5):683–695. doi: 10.1177/0165551517740835.
29. Rodrigues R, Camilo-Junior C, Couto T. A taxonomy for sentiment analysis field. Int J Web Inf Syst. 2018;14(2):193–211. doi: 10.1108/IJWIS-07-2017-0048.
30. Hajhmida MB, Oueslati O. Predicting mobile application breakout using sentiment analysis of Facebook posts. J Inf Sci. 2020. doi: 10.1177/0165551520917099.
31. Tung KC, Wang ET, Chen ALP. Mining event sequences from social media for election prediction. In: Perner P, ed. 16th Industrial Conference on Advances in Data Mining. Springer-Verlag. 2016;9728:266–281. doi: 10.1007/978-3-319-41561-1_20.
32. Taiwan Centers for Disease Control. CECC confirms 2 more imported COVID-19 cases; both cases arrive in Taiwan from the Philippines. Accessed February 20, 2021. https://www.cdc.gov.tw/En/Bulletin/Detail/TZJg2YtDrIuRvzEAmDf8JA?typeid=158
33. Google LLC. Google Translate. Accessed February 1, 2020. https://translate.google.com
34. Chiaramello E, Pinciroli F, Bonalumi A, Caroli A, Tognola G. Use of “off-the-shelf” information extraction algorithms in clinical informatics: a feasibility study of MetaMap annotation of Italian medical notes. J Biomed Inform. 2016;63:22–32. doi: 10.1016/j.jbi.2016.07.017.
35. Tarsoly E, Valijärvi RL. Language students as critical users of Google Translate: pitfalls and possibilities. Pract Res High Educ. 2019;12(1):61–74.
36. Ameur H, Jamoussi S, Hamadou AB. A new method for sentiment analysis using contextual auto-encoders. J Comput Sci Technol. 2018;33(6):1307–1319. doi: 10.1007/s11390-018-1889-1.
37. Chatzakou D, Vakali A, Kafetsios K. Detecting variation of emotions in online activities. Expert Syst Appl. 2017;89:318–332. doi: 10.1016/j.eswa.2017.07.044.
38. Windsor LC, Cupit JG, Windsor AJ. Automated content analysis across six languages. PLOS ONE. 2019.;14(11):14. doi: 10.1371/journal.pone.0224425.
39. Lima A, De Castro LN, Corchado JM. A polarity analysis framework for Twitter messages. Appl Math Comput. 2015;270:756–767. doi: 10.1016/j.amc.2015.08.059.
40. Textblob: Simplified Text Processing. TextBlob. 2020. Accessed February 1, 2020. https://textblob.readthedocs.io/en/dev/index.html
41. Hutto C, Gilbert E. VADER: a parsimonious rule-based model for sentiment analysis of social media text. In Proceedings of the International AAAI Conference on Web and Social Media. 2014.
42. Vermeer SAM, Araujo T, Bernritter SF, Noort GV. Seeing the wood for the trees: how machine learning can help firms in identifying relevant electronic word-of-mouth in social media. Int J Res Mark. 2019;36(3):492–508. doi: 10.1016/j.ijresmar.2019.01.010.
43. Wang YY, Bowers AJ, Fikis DJ. Automated text data mining analysis of five decades of educational leadership research literature: probabilistic topic modeling of EAQ articles from 1965 to 2014. Educ Adm Q. 2017;53(2):289–323. doi: 10.1177/0013161X16660585.
44. Taiwan Centers for Disease Control. Taiwan Centers for Disease Control, Facebook. Accessed February 15, 2020. https://www.facebook.com/TWCDC
45. Ministry of Health, Singapore. Ministry of Health Singapore. Accessed February 15, 2020. https://www.facebook.com/sghealthministry
46. Centers for Disease Control. CDC. Accessed February 15, 2020. https://www.facebook.com/CDC
47. Public Health England. Public Health England. Accessed February 15, 2020. https://www.facebook.com/PublicHealthEngland/
48. Jünger J, Keyling T. Facepager. An application for automated data retrieval on the web. Accessed February 1, 2021. https://github.com/strohne/Facepager/
49. Directorate-General of Budget, Accounting and Statistics. National Statistics of Republic of China (Taiwan). Accessed February 1, 2020. https://eng.stat.gov.tw/mp.asp?mp=5
50. Organisation for Economic Co-operation and Development. Population. Accessed February 1, 2020. https://www.oecd-ilibrary.org/content/data/d434f82b-en
51. Witten IH, Frank E, Hall MA, Pal CJ. Data Mining: practical machine learning tools and techniques. 4th ed. Morgan Kaufmann; 2016. Accessed February 1, 2020. https://www.cs.waikato.ac.nz/ml/weka/Witten_et_al_2016_appendix.pdf
52. Ali Z, Razzaq A, Ali S, Qadri S, Zia A. Improving sentiment analysis efficacy through feature synchronization. Multimed Tools Appl. 2021;80:13325–13338. doi: doi.org/10.1007/s11042-020-10383-w.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊