SECTION I: GENERAL INFORMATION ABOUT THE COURSE

Course Code	Course Name	Year	Semester	Theoretical	Practical	Credit	ECTS
BVA5106	Natural Language Processing Applications	1	Spring	1	2	2	6

Course Type :	Compulsory
Cycle:	Associate TQF-HE:5. Master`s Degree QF-EHEA:Short Cycle EQF-LLL:5. Master`s Degree
Language of Instruction:	Turkish
Prerequisities and Co-requisities:	N/A
Mode of Delivery:	Face to face
Name of Coordinator:	Instructor ÖZGE DEMİR
Dersin Öğretim Eleman(lar)ı:	Instructor ÖZGE DEMİR
Dersin Kategorisi:	Programme Specific

SECTION II: INTRODUCTION TO THE COURSE

Course Objectives & Content

Course Objectives:

The objective of this course is to introduce students to the fundamental concepts, methods, and tools of natural language processing (NLP) and to enable them to master the process of analyzing text-based data in a computer environment. Students will learn fundamental NLP techniques such as text data preprocessing, cleaning, feature extraction, and classification. They will also conduct practical work on sentiment analysis, text mining, and information extraction using Python and popular libraries such as NLTK and spaCy. The aim is to develop the ability to work with real-world text data to solve problems encountered in natural language processing projects and to keep up with current technologies in this field.

Course Content:

This course covers fundamental concepts, approaches, and application tools in the field of Natural Language Processing (NLP). The course begins by explaining the definition of NLP, its historical development, areas of application, and its relationship with other data science and artificial intelligence disciplines. The structure of text-based data, the main challenges encountered in processing natural language in a computer environment, and linguistic ambiguities are discussed.

The course then examines the process of preparing text data for analysis in detail. This includes fundamental preprocessing techniques such as text cleaning, normalization, tokenization, stop-word removal, stemming, and lemmatization. Bag-of-Words, TF-IDF, and n-gram-based feature extraction methods for extracting meaningful features from text data are introduced.

Following feature extraction, text classification problems and basic machine learning approaches to these problems are examined. Sentiment analysis, topic classification, and simple information extraction applications are performed on text data. This process involves practical exercises using the Python programming language and common natural language processing libraries such as NLTK and spaCy.

The course also covers the concept of text mining, the analysis of real-world text data, the interpretation of datasets, and the evaluation of model outputs. The aim is for students to recognize data quality problems that may be encountered in natural language processing projects, to select appropriate methods, and to develop problem-solving skills. The course provides an overview of current natural language processing applications, concluding with students acquiring the fundamental knowledge and competencies to keep up with technological advancements in this field.

Course Learning Outcomes (CLOs)

Course Learning Outcomes (CLOs) are those describing the knowledge, skills and competencies that students are expected to achieve upon successful completion of the course. In this context, Course Learning Outcomes defined for this course unit are as follows:



Knowledge *(Described as Theoritical and/or Factual Knowledge.)*
Skills *(Describe as Cognitive and/or Practical Skills.)*
1) Can apply data cleaning and preprocessing processes to natural language data.
Competences *(Described as "Ability of the learner to apply knowledge and skills autonomously with responsibility", "Learning to learn"," Communication and social" and "Field specific" competences.)*
1) It can perform NLP-based analysis and interpretation by working with real-world data sets.
2) Can use natural language processing methods in the analysis of text-based data.
3) Can apply data cleaning and preprocessing processes to natural language data.
4) Python programlama dili ile NLP projeleri geliştirebilir.

Weekly Course Schedule

Week	Subject	Materials Sharing *
		Related Preparation	Further Study
1)	Introduction and Basic Concepts
2)	Text Preprocessing and Statistical Models
3)	Word Embeddings
4)	Text Classification Applications
5)	Introduction to Deep Learning
6)	Recurrent Neural Networks (RNN) and LSTMs
7)	Transformer Architecture and Attention Mechanism
8)	Midterm
9)	Question-Answer Systems and Summarization
10)	Machine Translation and Text Generation
11)	Information Extraction and Entity Recognition
12)	Advanced Topics and Case Studies
13)	Large Language Models (LLM) and Their Applications
14)	Large Language Models (LLM) and Their Applications

*These fields provides students with course materials for their pre- and further study before and after the course delivered.

DERS ÖĞRENME ÇIKTILARI - PROGRAM ÖĞRENME ÇIKTILARI İLİŞKİSİ

Contribution of The Course Unit To The Programme Learning Outcomes

Ders Öğrenme Çıktıları (DÖÇ)	1	3	2	4	5
Program Öğrenme Çıktıları (PÖÇ)
1) It explains fundamental concepts in mathematics, statistics, and probability; and applies this knowledge to data analysis, modeling, and interpretation of results.
2) It explains the principles of algorithm design and develops software for solving problems using at least one programming language.
3) It compares machine learning and data mining algorithms, selects the appropriate method, and applies it to real data.
4) Big data platforms utilize distributed systems and cloud computing architectures to perform data processing operations.
5) They apply natural language processing techniques to text data and develop basic NLP-based applications.
6) It analyzes different data sources, transforms them into meaningful outputs, and presents them using appropriate visualization tools.
7) It creates data-driven decision models using decision support systems.
8) It develops optimization models and produces solutions for industrial and sectoral problems.
9) In professional practice, we operate within the framework of ethical principles, data security, and social responsibility.
10) They keep up with current technological developments in their field, actively participate in teamwork, and develop a lifelong learning awareness.

SECTION III: RELATIONSHIP BETWEEN COURSE UNIT AND COURSE LEARNING OUTCOMES (CLOs)

Level of Contribution of the Course to PLOs

No Effect	1 Lowest	2 Low	3 Average	4 High	5 Highest

	Programme Learning Outcomes	Contribution Level (from 1 to 5)
1)	It explains fundamental concepts in mathematics, statistics, and probability; and applies this knowledge to data analysis, modeling, and interpretation of results.
2)	It explains the principles of algorithm design and develops software for solving problems using at least one programming language.
3)	It compares machine learning and data mining algorithms, selects the appropriate method, and applies it to real data.
4)	Big data platforms utilize distributed systems and cloud computing architectures to perform data processing operations.
5)	They apply natural language processing techniques to text data and develop basic NLP-based applications.	5
6)	It analyzes different data sources, transforms them into meaningful outputs, and presents them using appropriate visualization tools.
7)	It creates data-driven decision models using decision support systems.
8)	It develops optimization models and produces solutions for industrial and sectoral problems.
9)	In professional practice, we operate within the framework of ethical principles, data security, and social responsibility.
10)	They keep up with current technological developments in their field, actively participate in teamwork, and develop a lifelong learning awareness.

SECTION IV: TEACHING-LEARNING & ASSESMENT-EVALUATION METHODS OF THE COURSE

Teaching & Learning Methods of the Course

(All teaching and learning methods used at the university are managed systematically. Upon proposals of the programme units, they are assessed by the relevant academic boards and, if found appropriate, they are included among the university list. Programmes, then, choose the appropriate methods in line with their programme design from this list. Likewise, appropriate methods to be used for the course units can be chosen among those defined for the programme.)

Teaching and Learning Methods defined at the Programme Level	Teaching and Learning Methods Defined for the Course
Lectures
Case Study
Homework
Project Preparation
Active Participation in Class

Assessment & Evaluation Methods of the Course

(All assessment and evaluation methods used at the university are managed systematically. Upon proposals of the programme units, they are assessed by the relevant academic boards and, if found appropriate, they are included among the university list. Programmes, then, choose the appropriate methods in line with their programme design from this list. Likewise, appropriate methods to be used for the course units can be chosen among those defined for the programme.)

Aassessment and evaluation Methods defined at the Programme Level	Assessment and Evaluation Methods defined for the Course
Final Exam
Homework Evaluation

Contribution of Assesment & Evalution Activities to Final Grade of the Course

Measurement and Evaluation Methods	# of practice per semester	Level of Contribution
Homework Assignments	1	% 15.00
Midterms	1	% 35.00
Semester Final Exam	1	% 50.00
Total		% 100
PERCENTAGE OF SEMESTER WORK		% 50
PERCENTAGE OF FINAL WORK		% 50
Total		% 100

SECTION V: WORKLOAD & ECTS CREDITS ALLOCATED FOR THE COURSE

WORKLOAD OF TEACHING & LEARNING ACTIVITIES
Teaching & Learning Activities	# of Activities per semester	Duration (hour)	Total Workload
Course	14	3	42
Laboratory	0	0	0
Application	14	3	42
Special Course Internship (Work Placement)	0	0	0
Field Work	0	0	0
Study Hours Out of Class	0	0	0
Presentations / Seminar	0	0	0
Project	0	0	0
Homework Assignments	10	1	10
Total Workload of Teaching & Learning Activities	-	-	94
WORKLOAD OF ASSESMENT & EVALUATION ACTIVITIES
Assesment & Evaluation Activities	# of Activities per semester	Duration (hour)	Total Workload
Quizzes	1	2	2
Midterms	20	1	20
Semester Final Exam	30	1	30
Total Workload of Assesment & Evaluation Activities	-	-	52
TOTAL WORKLOAD (Teaching & Learning + Assesment & Evaluation Activities)			146
ECTS CREDITS OF THE COURSE (Total Workload/25.5 h)			6

Course Notes / Textbooks:
References:	Natural Language Processing , Jacob Eisenstein