BUSANA 7005 - Chatbots and Text Analytics for Business
North Terrace Campus - Semester 2 - 2024
-
General Course Information
Course Details
Course Code BUSANA 7005 Course Chatbots and Text Analytics for Business Coordinating Unit Adelaide Business School Term Semester 2 Level Postgraduate Coursework Location/s North Terrace Campus Units 3 Available for Study Abroad and Exchange Y Course Staff
Course Coordinator: Dr Ilker Cingillioglu
Course Timetable
The full timetable of all activities for this course can be accessed from .
Week
Topic
Learning activity
Learning outcome
1
Module 1: Overview of Chatbots and Text Analytics for Business
Lecture
LO1
2
Module 1: Business Applications of Chatbots and Text Analytics
Lecture
LO1
3
Module 2: Foundations of Textual Data Processing
Lecture
LO2
4
Module 2: Structure of Language and Natural Language Processing (NLP)
Lecture
LO1
5
Module 3: Text Representation: The Vector Space Model (VSM)
Lecture
LO2
6
Module 4: Similarity, Clustering and Topic Modelling
Lecture
LO2, LO4
7
Module 5: Lexical Semantics and Sentiment Analysis
Lecture
LO2, LO4
8
Module 6: Advanced Text Classification with Large Language Models (LLMs)
Lecture
LO2, LO4
9
Module 7: Introduction to Chatbots and Chatbot Development
Lecture
LO3
10
Module 7: Scripted Chatbot Development
Lecture
LO3, LO4
11
Module 8: Generative (AI-driven) Chatbot Development
Lecture
LO3, LO4
12
Module 8: Generative (AI-driven) Chatbot Development
Lecture
LO3, LO4
-
Learning Outcomes
Course Learning Outcomes
On successful completion of this course students will be able to:
- Understand the use of chatbots and text analytics in real-life business applications.
- Demonstrate basic proficiency in Python programming, including data manipulation, text analytics and API integrations.
- Implement functional chatbots and understand the principles of developing scripted (rule-based) and generative (AI-based) chatbots.
- Analyse challenges and devise innovative solutions that combine Python programming, chatbot development and text analytics within the business environment.
University Graduate Attributes
This course will provide students with an opportunity to develop the Graduate Attribute(s) specified below:
University Graduate Attribute Course Learning Outcome(s) Attribute 1: Deep discipline knowledge and intellectual breadth
Graduates have comprehensive knowledge and understanding of their subject area, the ability to engage with different traditions of thought, and the ability to apply their knowledge in practice including in multi-disciplinary or multi-professional contexts.
1, 2, 3, 4 Attribute 2: Creative and critical thinking, and problem solving
Graduates are effective problems-solvers, able to apply critical, creative and evidence-based thinking to conceive innovative responses to future challenges.
3, 4 Attribute 3: Teamwork and communication skills
Graduates convey ideas and information effectively to a range of audiences for a variety of purposes and contribute in a positive and collaborative manner to achieving common goals.
4 Attribute 4: Professionalism and leadership readiness
Graduates engage in professional behaviour and have the potential to be entrepreneurial and take leadership roles in their chosen occupations or careers and communities.
4 Attribute 7: Digital capabilities
Graduates are well prepared for living, learning and working in a digital society.
1, 2, 3, 4 -
Learning Resources
Required Resources
There is no mandatory texbook for this course as the required resources will vary by teaching period to stay in touch with the latest development in the NLP/chatbot/prompt engineering space.Recommended Resources
- 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.
- "Python for Data Analysis" by Wes McKinney: A comprehensive guide to utilizing Python for data manipulation, analysis, and visualization.
- “Brex's Prompt Engineering Guide” ()
- "The Prompt Engineering Cookbook" ()
- “Lil'Log Prompt Engineering” ()
Online Learning
- 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.
- 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.
- 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.
- Online Textbooks and other Learning Material:
-
Learning & Teaching Activities
Learning & Teaching Modes
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.
Workload
The information below is provided as a guide to assist students in engaging appropriately with the course requirements.
Over the course of 13 weeks, a total of 12 seminars will be conducted, each lasting 3 hours. The expected workload for the entire semester, including all readings and preparations, is approximately 150 hours, which averages to about 11.53 hours per week.Learning Activities Summary
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.
Specific Course Requirements
The course-specific requirements include access to a personal laptop, a Google account, an IBM Cloud account, and an OpenAI account (online resources are available for free). -
Assessment
The University's policy on Assessment for Coursework Programs is based on the following four principles:
- Assessment must encourage and reinforce learning.
- Assessment must enable robust and fair judgements about student performance.
- Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
- Assessment must maintain academic standards.
Assessment Summary
Assessment Task Task Type Due Date Course Learning Outcome(s) being assessed Assessment
WeightingQuizzes Formative and Summative Throughout the teaching period with deadlines set for each piece of work a day before the following teaching session.
1,2,3 20% Group Assignment Summative Two weeks following the last class 4 30% Final Exam Summative Last class 1,2,3,4 50% Assessment Detail
- 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.
- 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.
- 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.
Submission
All submissions are to be made online through the course's MyUni page.Course Grading
Grades for your performance in this course will be awarded in accordance with the following scheme:
M10 (Coursework Mark Scheme) Grade Mark Description FNS Fail No Submission F 1-49 Fail P 50-64 Pass C 65-74 Credit D 75-84 Distinction HD 85-100 High Distinction CN Continuing NFE No Formal Examination RP Result Pending Further details of the grades/results can be obtained from Examinations.
Grade Descriptors are available which provide a general guide to the standard of work that is expected at each grade level. More information at Assessment for Coursework Programs.
Final results for this course will be made available through .
-
Student Feedback
The University places a high priority on approaches to learning and teaching that enhance the student experience. Feedback is sought from students in a variety of ways including on-going engagement with staff, the use of online discussion boards and the use of Student Experience of Learning and Teaching (SELT) surveys as well as GOS surveys and Program reviews.
SELTs are an important source of information to inform individual teaching practice, decisions about teaching duties, and course and program curriculum design. They enable the University to assess how effectively its learning environments and teaching practices facilitate student engagement and learning outcomes. Under the current SELT Policy (http://www.adelaide.edu.au/policies/101/) course SELTs are mandated and must be conducted at the conclusion of each term/semester/trimester for every course offering. Feedback on issues raised through course SELT surveys is made available to enrolled students through various resources (e.g. MyUni). In addition aggregated course SELT data is available.
-
Student Support
- Academic Integrity for Students
- Academic Support with Maths
- Academic Support with writing and study skills
- Careers Services
- Library Services for Students
- LinkedIn Learning
- Student Life Counselling Support - Personal counselling for issues affecting study
- Students with a Disability - Alternative academic arrangements
-
Policies & Guidelines
This section contains links to relevant assessment-related policies and guidelines - all university policies.
- Academic Credit Arrangements Policy
- Academic Integrity Policy
- Academic Progress by Coursework Students Policy
- Assessment for Coursework Programs Policy
- Copyright Compliance Policy
- Coursework Academic Programs Policy
- Intellectual Property Policy
- IT Acceptable Use and Security Policy
- Modified Arrangements for Coursework Assessment Policy
- Reasonable Adjustments to Learning, Teaching & Assessment for Students with a Disability Policy
- Student Experience of Learning and Teaching Policy
- Student Grievance Resolution Process
-
Fraud Awareness
Students are reminded that in order to maintain the academic integrity of all programs and courses, the university has a zero-tolerance approach to students offering money or significant value goods or services to any staff member who is involved in their teaching or assessment. Students offering lecturers or tutors or professional staff anything more than a small token of appreciation is totally unacceptable, in any circumstances. Staff members are obliged to report all such incidents to their supervisor/manager, who will refer them for action under the university's student鈥檚 disciplinary procedures.
The 成人大片 is committed to regular reviews of the courses and programs it offers to students. The 成人大片 therefore reserves the right to discontinue or vary programs and courses without notice. Please read the important information contained in the disclaimer.