教學大綱 Syllabus

科目名稱:文字探勘與商業應用

Course Name: Text Mining Applications in Business

修別:選

Type of Credit: Elective

3.0

學分數

Credit(s)

15

預收人數

Number of Students

課程資料Course Details

課程簡介Course Description

Text mining is an attractive area in artificial intelligence today. With the progress of machine learning, the power of text mining has been shown in novel applications in various domains. In the business area, text mining helps businesses to discover useful information from large and heterogeneous data, solve the information overload problem, and create value for organizations and societies.

The first part of the course will introduce the components and techniques of text mining. Then, after the midterm exam, the students will learn the applications of text mining in various topics and handle textual data to solve business problems in every-week labs. The students are expected to analyze real-world data with text mining techniques and provide insights into the final project.

核心能力分析圖 Core Competence Analysis Chart

能力項目說明


    課程目標與學習成效Course Objectives & Learning Outcomes

    • Understand the components and techniques of text mining and possible applications in the business area.
    • Be familiar with basic text mining tools and the most recent progress in text mining.
    • Learn how to handle textual data with text mining techniques and solve business problems.

    每周課程進度與作業要求 Course Schedule & Requirements

    教學週次Course Week 彈性補充教學週次Flexible Supplemental Instruction Week 彈性補充教學類別Flexible Supplemental Instruction Type

    Week

    Subject

    1

    • Introduction to text processing
    • Linguistics essentials: lexicon, syntax, semantics, etc.
    • Corpus

    2

    • Language modeling: Markov assumption, n-gram model, probabilities estimation, etc.
    • Model evaluation: metrics and tests

    3

    • Preprocessing , Word segmentation

    4

    • Text classification:

    classifier, feature extraction (BOW, naïve bayes model, logistic regression, decision tree…), overfitting, etc.

    • Word sense disambiguation

    5

    • POS tagging
    • Sequence labeling: HMM, MEMM, NER, etc.

    6

    • Word embedding and neural network
    • Parsing and discourse analysis

    7

    Talk (Alternative class)

    8

    review (彈性授課)

    9

    Midterm-exam

    10

    Introduction to text mining applications

    11

    Topic: voice recognition and sentiment analysis

    12

    seminar

    13

    Topic: auto summarization, auto correction, and auto translation

    14

    seminar

    15

    Topic: chat robot, virtual assistant (or recommender systems) and social listening

    16

    review (彈性授課)

    17

    Final project presentation

    18

    Final-exam

    授課方式Teaching Approach

    40%

    講述 Lecture

    20%

    討論 Discussion

    30%

    小組活動 Group activity

    10%

    數位學習 E-learning

    0%

    其他: Others:

    評量工具與策略、評分標準成效Evaluation Criteria

    30%

    Exams

    30% Lab / Assignments

     

    30%

    Project

    10%

    Participation

    Possible venue: https://aidea-web.tw/aicup_meddialog
    A team should consist of 3 to 5 members

    • F1-score of the official formal run (40%)
    • Report (60%)
      - Your methodology

    - Innovation

    - Analysis of the results

    指定/參考書目Textbook & References

    已申請之圖書館指定參考書目 圖書館指定參考書查詢 |相關處理要點

    維護智慧財產權,務必使用正版書籍。 Respect Copyright.

    課程相關連結Course Related Links

    
                

    課程附件Course Attachments

    課程進行中,使用智慧型手機、平板等隨身設備 To Use Smart Devices During the Class

    需經教師同意始得使用 Approval

    列印