| Academic Unit: |
Computer Engineering Department |
| Mode of Delivery: |
Face to face |
| Prerequisites: |
None |
| Language of Instruction: |
English |
| Level of Course Unit: |
Undergraduate |
| Course Coordinator: |
Rahim DEHKHARGHANİ |
| Course Lecturer(s): |
Rahim DEHKHARGHANİ |
| Course Objectives: |
This course aims to provide general and task-specific knowledge of analyzing textual data types to extract useful information. Students will practically work on a problem using text mining techniques to extract the mentioned information. They can use any programming language for this purpose but Python will be used during the lectures to implement the taught theoretical techniques in the theoretical part of the course. At the end of the semester, students must be able to preprocess textual data and prepare them for the main task such as spell correction, POS tagging, text classification, semantic analysis, sentiment analysis, and so on. |
| Course Contents: |
The course will cover topics such as text preprocessing and normalization, regular expressions, spell correction, POS tagging, sentiment analysis, text classification and naïve Bayes, classification and evaluation of classification algorithms, Word semantics and Word Embeddings. |
| Learning Outcomes of the Course Unit (LO): |
- 1- Ability to Preprocess, and analyze the textual data to understand it.
- 2- Ability to implement the NLP techniques of this course such as spell correction, text classification and POS tagging using a programming language such as Python.
- 3- Ability to use a programming language such as Python and its libraries to perform classification, and clustering on textual data.
|
| Planned Learning Activities and Teaching Methods: |
In-class learning. Programming homework will be done individually. But design and implementation of a solution for a real-world problem will be done as a group work. All theoretical concepts taught in this course will be implemented in its coding section. |
| Week | Subjects | Related Preperation |
| 1 |
Introduction to NLP and Python |
Lecture slides and reading material |
| 2 |
Text processing and Regular expressions |
Lecture slides and reading material |
| 3 |
Text processing and Regular expressions |
Lecture slides and reading material |
| 4 |
Minimum Edit Distance |
Lecture slides and reading material |
| 5 |
N-gram language models and LLMs |
Lecture slides and reading material |
| 6 |
Text classification and Naïve Bayes |
Lecture slides and reading material |
| 7 |
Spell correction |
Lecture slides and reading material |
| 8 |
POS tagging and Live Project 1 |
Lecture slides and reading material |
| 9 |
Vector semantics |
Lecture slides and reading material |
| 10 |
Sentiment Analysis |
Lecture slides and reading material |
| 11 |
Affective analysis and Emotions |
Lecture slides and reading material |
| 12 |
Introduction to Word embeddings |
Lecture slides and reading material |
| 13 |
Word Semantic and relations |
Lecture slides and reading material |
| 14 |
Live Project 2 |
Lecture slides and reading material |
At Kadir Has University, a Semester is 14 weeks; The weeks 15 and 16 are reserved for final exams.
THE RELATIONSHIP BETWEEN COURSE LEARNING OUTCOMES (LO) AND PROGRAM QUALIFICATIONS (PQ)
| # |
PQ1 |
PQ2 |
PQ3 |
PQ4 |
PQ5 |
PQ6 |
PQ7 |
PQ8 |
PQ9 |
| LO1 |
|
|
|
|
|
|
|
|
|
| LO2 |
|
|
|
|
|
|
|
|
|
| LO3 |
|
|
|
|
|
|
|
|
|
Contribution: 1 Low, 2 Average, 3 High
