IA 340: Data Mining, Modeling, and Knowledge Discovery in Databases

IA 340: Data Mining, Modeling, and Knowledge Discovery in Databases

Course / Term / Instructor

• Course: IA 340: Data Mining, Modeling, and Knowledge Discovery in Databases
• Term: Fall 2026
• Instructor: Dr. Xuebin Wei (weixx@jmu.edu)
• Office Hours: Monday and Wednesday, 9:30–11:00 AM

---

Course Description

This course provides a comprehensive introduction to modern Data Analytics, Cloud Databases, and AI integration. Moving beyond basic spreadsheets, we explore data processing pipelines, relational and NoSQL databases, and apply Large Language Models (LLMs) to practical data mining scenarios.

Learning Goals

Upon completion of this course, students are expected to:

• Differentiate and design relational and NoSQL databases, and manage cloud-based storage solutions.
• Collect, query, and analyze real-world data using SQL, MQL, Python, and cloud services.
• Apply AI-powered methods (LLMs, vector databases) to support data analytics.
• Address ethical and security considerations in data management and analysis.

IA340 Learning Journey

PHASE 1 — Cloud Data & Python ☁️

Google Colab

↳ Google Drive / cloud object storage / data lake concept (e.g., S3 principles)

↳ Python / Pandas

↳ cleaning / quantitative analysis

PHASE 2 — Relational Data 🗄️

Data modeling / ER

↳ relational database

↳ SQL

↳ Python + AI-assisted SQL/query workflows

PHASE 3 — NoSQL / Social / API Data 🌐

APIs / social data

↳ MongoDB

↳ query / aggregation

↳ embeddings / vector search

↳ AI-assisted analysis

PHASE 4 — Final Project 🎓

end-to-end data collection / storage / analysis workflow

Required Textbook & Account Setup

• Textbook: Wei, Xuebin, and Xinyue Ye. Social Data Analytics in the Cloud with AI. CRC Press / Routledge, 2024. (Note: Refer to Canvas for any specific JMU free-access instructions for required materials.)
• Google Account (Required): You must use your James Madison University email address (@dukes.jmu.edu or @jmu.edu) to create or link a Google account for accessing Google Colab, Drive, and cloud datasets.
• GitHub Account (Required): Required for accessing course repositories, lab materials, and submitting technical work.
• Coursera JMU AI Program (Required): Required for completing the Google AI Professional Certificate component.
• Google AI Pro / Gemini Advanced (Optional — Zero Grade Impact): Google offers an optional 1-year free student subscription for Gemini Advanced. Because this promotion requires personal payment details and third-party document verification, students are not required to sign up, and opting out has zero impact on your grade. (If verifying, students are strongly advised not to upload sensitive documents like official academic transcripts).

Email Communication

• Primary Contact: Emailing the instructor from your JMU student account is the primary method of communication.
• Response Time: The instructor typically responds within 1–2 business days. Emails received after 5:00 PM will be treated as received on the next business day. The instructor does not normally respond to emails on weekends or JMU holidays.
• Canvas Usage: Canvas is strictly used for grades, official announcements, and basic course logistics. Do not use Canvas messaging to contact the instructor; it is not regularly monitored.

AI Policy

AI is part of this course, and may be expected or required in specific assignments. You may use Artificial Intelligence (e.g., LLMs, coding assistants) to assist with data analysis and workflow construction as instructed. However, you are strictly responsible for the output you submit. You must inspect, test, verify, correct, and explain any AI-assisted work. Blindly copying and pasting AI output without understanding it is a violation of the learning objectives and academic integrity.

Grading Breakdown

Category	Weight
Attendance	20%
Labs	40%
Projects (Total)	30%
- Mini Project	10%
- Final Project	20%
Google AI Professional Certificate	10%

Google AI Professional Certificate Progress:

• Completion of 1 module/course = 3%
• Completion of 2 modules/courses = 6%
• Completion of 3 or more modules/courses = 10%

Letter-Grade Scale

• A: 94.00 – 100%

  A-: 90.00 – 93.99%

• B+: 87.00 – 89.99%

  B: 84.00 – 86.99%

  B-: 80.00 – 83.99%

• C+: 77.00 – 79.99%

  C: 74.00 – 76.99%

  C-: 70.00 – 73.99%

• D+: 67.00 – 69.99%

  D: 64.00 – 66.99%

  D-: 61.00 – 63.99%

• F: < 61%

Technical Assignment Support

Technical assignments may require troubleshooting. Start assignments early and allow sufficient time to resolve technical issues. Requests for assistance made shortly before a deadline may not receive a response before the deadline and do not automatically excuse late submissions.

Resubmission / Late Work / Project Policy

• Resubmission: You are allowed to resubmit assignments multiple times before the deadline. Only the final submission made prior to the deadline will be graded.
• Late Work: Late submissions will incur a 10% penalty per day, but no more than 40% of the total amount, unless prior arrangements have been made.
• Final Exam Week: No late submissions will be accepted during the final exam week.
• Class Projects: Late submissions/resubmissions of the class projects will not be accepted.

Attendance & Registered Section Policy

Attendance is mandatory and constitutes a significant portion (20%) of your grade. Attendance will be taken at every class meeting. Absence, early leaving without permission, being late more than 20 minutes, or disrespectful/disturbing behavior will result in 0 points each time. Being late more than 5 minutes will result in a late penalty.

• Registered Section Attendance: Students must attend the course section in which they are officially registered unless the instructor approves an exception in advance.
• Excused Absences: In the following situations, absences can be excused:
  • Sickness or health issues.
  • Mandatory activities with written documents.
  • Other situations with the instructor’s approval.

Academic Integrity / Honor Code

All students are expected to adhere to the JMU Honor Code. While AI use is permitted and encouraged as defined in the AI policy, plagiarizing another student’s work, fabricating data, or presenting unverified AI output as original thought without proper testing and explanation is strictly prohibited and will be reported to the Honor Council.

Accessibility / Student Support

JMU is committed to creating a universally accessible learning environment. If you have a documented disability and require accommodations, please register with the Office of Disability Services (ODS, https://www.jmu.edu/ods/) and contact the instructor as soon as possible so we can implement your approved accommodations.

JMU offers numerous resources to support your academic and personal success. If you are struggling, please reach out:

• JMU Counseling Center: Support for mental health and well-being.
• Learning Centers: Tutoring and academic support.

Inclement Weather

During the semester, there may be days during which the class will not meet due to inclement weather. Please check Canvas for the latest class arrangement and refer to the official JMU policy on inclement weather.

---

Course Schedule (Fall 2026)

Schedule updated: August 28, 2026

Week	Dates	Topic	Key Concepts & Hands-on Activities	Notes / Milestones
Week 1	Aug 24–28	Introduction & Account Setup	• Course introduction • Required account and environment setup	Classes begin Wednesday, Aug 26
Week 2	Aug 31–Sep 4	GitHub, Colab & Google Drive Setup	• Create and configure individual GitHub repository • README and Markdown basics • Demonstrate branch / Pull Request / merge workflow • Set up Google Colab & connect to Google Drive • Load sample diamonds dataset • Save and share notebook via GitHub
Week 3	Sep 7–11	Pandas & Matplotlib Review	• Pandas data analysis • AI-assisted coding and explanation with demo notebook & Colab/Gemini • Matplotlib data visualization using the same dataset
Week 4	Sep 14–18	Relational Database, Google Cloud & ER Diagram	• Set up a relational database on Google Cloud • Relational database concepts • ER diagrams • Create database tables
Week 5	Sep 21–25	Database Connection, SQL & Census API	• Connect from Colab to cloud database • Basic SQL queries and INSERT • Census API integration • Load API data into the relational database
Week 6	Sep 28–Oct 2	SQL Analytics & Visualization	• Advanced SQL queries (JOIN, GROUP BY, aggregation) • Analyze query results with Python/Pandas • Visualization of query results
Week 7	Oct 5–9	Mini Project	• Students independently identify a dataset • AI-assisted data analysis • Data stored in Google Drive, relational database, or course workflows • Final deliverable: reproducible notebook in student GitHub repo	Fall Break begins Oct 7
Week 8	Oct 12–16	NoSQL & MongoDB	• Relational vs. NoSQL databases • Document database concepts • MongoDB setup • JSON / document structure • Basic MongoDB operations
Week 9	Oct 19–23	Social Media Data Collection & Document Queries	• Collect Twitter/X or course-provided social media data • Store data in MongoDB • Document queries
Week 10	Oct 26–30	MongoDB Aggregation & Natural Language Queries	• MongoDB aggregation pipeline • Filtering, grouping, and aggregation • AI / natural-language-assisted queries
Week 11	Nov 2–6	Large Language Models for Vector Database RAG for Social Media Analysis	• LLM foundations & rationale for text analysis • Prompt engineering & calling LLM API from Python/Colab • Process social-media text (classification, extraction, sentiment, summarization) • Embeddings, vector databases, semantic search & Retrieval-Augmented Generation (RAG)
Week 12	Nov 9–13	Dashboard for Natural Language Analytics	• Build analytical dashboards using MongoDB/social-media analysis results • Natural-language-assisted analysis and visualization
Week 13	Nov 16–20	Gemini Notebook for LLM	• Gemini and NotebookLM workflows • Integrate generative AI tools with data-analysis workflows
Week 14	Nov 23–27	Thanksgiving Holiday	No Class	Thanksgiving Holiday (No Class)
Week 15	Nov 30–Dec 4	Final Project (Part 1)	• Standardized social-media analytical pipeline:   1. Collect Twitter/X/social-media data   2. Store data in MongoDB   3. Perform database/data analysis   4. Apply LLM-assisted text analysis   5. Build a shareable analytical dashboard   6. Maintain project code/docs in GitHub	Final Project in progress
Week 16	Dec 7–11	Final Project (Part 2)	• Final project implementation & refinement • Complete analytical dashboard & reproducible Colab notebook • Code cleanup, documentation & GitHub repository finalization	Final Project in progress
Week 17	Dec 12–18	Final Exam Week — Final Project Submission	• Students submit the completed Final Project • No final presentation	Final Project Due (No late submissions during exam week)

---

← Return to Course Home | Go to Module 1 →