On successful completion of this course students will be able to:

1. Understand the use of chatbots and text analytics in real-life business applications. 
2. Demonstrate basic proficiency in Python programming, including data manipulation, text analytics and API integrations. 
3. Implement functional chatbots and understand the principles of developing scripted (rule-based) and generative (AI-based) chatbots. 
4. Analyse challenges and devise innovative solutions that combine Python programming, chatbot development and text analytics within the business environment.

1. Online Textbooks and other Learning Material:
   • "Natural Language Processing with Python" by Steven Bird, Ewan Klein, and Edward Loper: Offers insights into NLP concepts and techniques using Python. https://www.nltk.org/book/
   • "Python for Data Analysis" by Wes McKinney: A comprehensive guide to utilizing Python for data manipulation, analysis, and visualization. https://wesmckinney.com/book/
   • “Brex's Prompt Engineering Guide” (https://github.com/brexhq/prompt-engineering)
   • "The Prompt Engineering Cookbook" (https://github.com/openai/openai-cookbook/blob/main/techniques_to_improve_reliability.md)
   • “Lil'Log Prompt Engineering” (https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/)

1. Online Platforms:
   • IBM Watson: A user-friendly platform for designing, building, and deploying intelligent chatbots that engage users in natural language conversations.
   • Google Colab: A user-friendly free cloud-based interactive development environment (IDE) for Python programming and experimentation.
   • GitHub: Collaborative version control platform for sharing code, assignments, and projects.
   • OpenAI Playground: An interactive interface for crafting and testing prompts for AI models.
2. Databases and Datasets:
   • Kaggle Datasets: A platform offering various datasets for NLP and AI projects.
   • OpenAI GPT-3.5/4 API: For accessing and experimenting with NLP models.
3. Programming Tools:
   • Python 3.x: The core programming language for the course, enabling students to develop AI applications.
   • Anaconda Distribution: Bundled with essential Python libraries for data analysis, providing a convenient environment for development.

1. Project-Based Learning (PBL):

Pedagogy: Students will work on projects throughout the course, starting from ideation to deployment of chatbots and text analytics solutions. These projects will directly address the CLOs and provide hands-on experience with the skills required in the field.

Rationale: PBL allows students to engage in real-world projects that simulate the challenges they will face in real life. This approach fosters critical thinking, problem-solving skills, and collaboration, aligning well with the course's emphasis on practical application.

2. Collaborative Learning:

Pedagogy: Group projects and discussions will be incorporated into the course structure. Students will collaborate on tasks such as developing chatbots, analysing text data, and devising solutions to business challenges. Peer feedback and review sessions will also be conducted to promote collaborative learning.

Rationale: Collaboration mirrors the teamwork often required in business environments, where people with diverse skills work together towards common goals. It encourages communication, peer learning, and the exchange of ideas and perspectives.

3. Active Learning:

Pedagogy: Activities such as coding exercises, case studies, and hands-on workshops will be included to encourage active participation. In-class discussions, debates, and problem-solving sessions will prompt students to apply their knowledge in practical scenarios.

Rationale: Active learning methods keep students engaged and promote deeper understanding and retention of concepts compared to passive learning approaches. Given the technical nature of the subject matter, active learning techniques help students stay actively involved in their learning process.

4. Flipped Classroom:

Pedagogy: Course materials such as lectures, tutorials, and supplementary resources will be made available online for students to review before class sessions. Class time will then be dedicated to active learning activities, project work, and clarifying concepts through discussions and demonstrations.

Rationale: The flipped classroom model allows students to engage with course materials outside of class, freeing up class time for interactive discussions, problem-solving, and hands-on activities. This approach promotes self-directed learning and deeper comprehension of complex topics.

5. Inquiry-Based Learning:

Pedagogy: Students will be encouraged to explore topics of interest within the realm of chatbots and text analytics through self-directed inquiry projects. They will formulate research questions, conduct investigations using relevant resources, and present their findings to peers and instructors.

Rationale: Inquiry-based learning encourages students to ask questions, explore topics independently, and construct their own understanding of concepts. It promotes curiosity, critical thinking, and problem-solving skills, which are essential for success in a rapidly evolving field like AI and analytics.

6. Formative and Summative Assessment:

Pedagogy: Formative assessment techniques such as quizzes and tests will be used throughout the course to gauge student understanding and provide feedback. Summative assessments such as project written reports, and practical exams will evaluate students' overall proficiency in meeting course learning outcomes.

Rationale: Formative assessment provides ongoing feedback to students, helping them monitor their progress and identify areas for improvement. Summative assessment evaluates student learning at the end of a course or unit, determining the extent to which learning outcomes have been achieved.

Module 1 - Overview and business applications of chatbots and text analytics

This introductory module is tailored for students seeking a foundational understanding of text analytics and the transformative potential of chatbots in diverse business settings.

Module 2 - Foundations of Textual Data Processing, Structure of Language and Natural Language Processing (NLP)

This module is designed to provide students with a comprehensive understanding of the intricacies involved in working with textual data as they will be equipped, by the end of this module, with the foundational knowledge and practical skills necessary to navigate the complexities of preparing and processing text for more advanced textual analyses.

Module 3 – Text Representation: The Vector Space Model

This module will explore the Vector Space Model, gaining insights into the conceptualization of documents as vectors and their applications in business. 

Module 4 - Similarity, Clustering and Topic Modelling 

This module covers the fundamental principles of text similarity, clustering, and topic modelling within the context of NLP.

Module 5 - Lexical Semantics and Sentiment Analysis

This module is designed to equip students with a broad understanding of lexical semantics and sentiment analysis. 

Module 6 - Advanced Text Classification with Large Language Models

This module offers a comprehensive exploration of advanced text processing, focusing on large language models.

Module 7 - Introduction to Chatbots and Chatbot Development 

This module equips students with the knowledge and practical skills needed to excel in the dynamic landscape of chatbot development. 

Module 8 - Transformers and Generative AI Chatbots

In this comprehensive module, students will delve into the intricate workings of transformer models and generative AI chatbots.

1. Quizzes (Weighting 20%): Quizzes will assess students' comprehension of the course material and their ability to apply chatbot development and text analytics concepts to given real-life problems. These quizzes are designed to cover various topics and difficulty levels, ensuring a comprehensive evaluation of knowledge and skills. The weighting of 20% reflects the significance of ongoing assessment and regular engagement with the content. Quizzes will provide timely feedback, enabling students to gauge their progress and address any areas of weakness before their group project and final exam. Quizzes will be open book/source and students can use GenAI providing adaptive and immediate feedback and making the learning process more engaging and effective.

2. Group Project (Weighting 30%): This assessment task will involve students working collaboratively to design, develop, and present an AI-driven application that showcases their chatbot development, programming, and text analytics skills. Each group will identify a real-world business problem or scenario where their application or solution can provide significant value. Using thinking skills, students will collaborate on coding, chatbot architecture, prompt design, and project management, demonstrating their ability to integrate concepts learned in the course. The project's substantial weighting of 30% emphasizes its role in assessing teamwork, creativity, technical proficiency, and the application of technical concepts to business problems.

3. Final Test/exam (Weighting 50%): The final exam will be a comprehensive assessment covering the entirety of the course material. It will test students' grasp of business and text analytics skills, and their ability to solve complex business problems. The weighting of 50% reflects the exam's role in evaluating students' overall understanding and retention of key concepts. The exam may include a mix of multiple-choice questions, coding exercises, short-answer questions, and prompts that challenge students to apply their knowledge to practical business and management scenarios. It will be open book/source and students are allowed to use GenAI providing adaptive and immediate feedback and making the learning process more engaging and effective.