Text Mining

TextMining_2020_EE100098 (MS_Team)
Time: Tue, 9:10am~12:00am, Room: I627
jdwang@asia.edu.tw, Room:I517, ext:1847
Pre-Requests
Some knowledge of Python Programming or any other programming languages

Score

Text Books
Text Analytics with Python: A Practitioner's Guide to Natural Language Processing (2nd version) Sarkar, Dipanjan,2019-05-22,ISBN-13:9781484243534
code-downloads
Book_TextAnalyticswithPython_Notes.html

References books
  • Hands-On Python Natural Language ProcessingAman Kedia , Mayank Rasu, 2020-06-26, ISBN-13:9781838989590
    code-downloads
    code-downloads (github)
  • Python Data Science Handbook (2015) Jake VanderPlas
  • Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition(2017) Sebastian Raschka, Vahid Mirjalil
    • 週次 日期 課程內容

    Weeks Date Course content

    1 2020/9/22 Introduction (Note: the rules of grading was modified)
    2 2020/9/29 Python for NLP
    3 2020/10/6 Text PreProcessing
    4 2020/10/13 Traditional Feature Engineering Models
    5 2020/10/20 Advanced Feature Engineering Model
    6 2020/10/27 Text Classification-Vectorization
    7 2020/11/3 Text Classification-Classifiers
    8 2020/11/10 Middle Project Presentation
    9 2020/11/17 Middle Project Report
    10 2020/11/24 Text Similarity
    11 2020/12/1 Text Clustering
    12 2020/12/8 Text Cluster- Visualization
    13 2020/12/15 Text Mining vs. Deep Learning(1)
    14 2020/12/22 Text Mining vs. Deep Learning(2)
    15 2020/12/29 AWS Educate program and AWS Academy program
    AWS Educate
    How to activate AWS Educate registration mail (如何回覆AWS確認信)(Thanks for Sharon)感謝 張倖瑜同學 提供(2020/3/13)(Thanks for Sharon
    AWS Educate Login
    How to go to AWS Educate Program Classroom(學生如何登入課程)(Thanks for Sharon)感謝 張倖瑜 同學 提供(2020/12/5)
    16 2021/1/5 Text Mining vs. AWS
    17 2021/1/12 Final Project presentation: Text Mining + AWS
    18 2021/1/19 Final Project (Report): Text Mining + AWS
    Grade
    Attendance (10%) +10 if you attend every week on time, Absent (-1/per week), Late (-0.5/per week)
    Homework 1 (10%): Text Preprocessing :　　Top 10 CancerTypes in PubMed ((2020/10/28 report (word(pdf)+YouTube(URL:sharing)) to moodle)

    Middle Project (30%): (2020/11/10, presentation (ppt))(2020/11/17 report (word(pdf)+YouTube(URL:sharing)) to moodle)

    (2~4 students/per group)(Text Classification :　Pubmed articels classification with top 10 cancertypes)
    Group (11/3), Presentation Schedule(11/10) and Score
    Homework 2 (10%): Text Clustering　　Document Clustering with Pubmed articles derived from Top 10 Cancertypes (2020/12/15 report (word(pdf)+YouTube(URL:sharing)) to moodle)

    Final Project (40%): (2~4 students/per group)(AWS+TextMining)<(2021/1/12, presentation (ppt), 2021/1/19 report (word(pdf)+YouTube(URL:sharing)) to moodle)

    Multi-languages Communication Online via AWS services
    Try to integrate AWS services to provide communications without the bottlenecks of using different languages in the world.
    Group Setup (1/5), Presentation(1/12) and Report to Moodle (1/19)
    References
    Computational Platform in AWS : To someones without sufficient computing power when handling with Big Data)
    AWS Educate Program (Apply Acount)
    AWS Educate Login

    Apply for an AWS Educate (By Suca)
    AWS Educate Program Information