Durham University
Programme and Module Handbook

Undergraduate Programme and Module Handbook 2026-2027

Module COMP3771: Applications of AI

Department: Computer Science

COMP3771: Applications of AI

Type Open Level 3 Credits 20 Availability Available in 2026/2027 Module Cap Location Durham

Prerequisites

  • COMP2261 Artificial Intelligence

Corequisites

  • None

Excluded Combination of Modules

  • None

Aims

  • To explore and apply frameworks, methods, and ethical principles for designing and evaluating Human-AI interactive systems.
  • To explore and apply recommender systems (RS) techniques and methods.

Content

  • Foundations of Human-AI Interaction (HAII)
  • Design and Evaluation Methods for HAII
  • Affective Computing in Human-AI Interaction
  • Trustworthy Autonomous Systems and Trust in AI
  • Responsible AI: Frameworks and Practices
  • Key RS techniques and traditional methods: content-based and collaborative filtering, hybrid and context-aware recommenders
  • Advances and state-of-the-art in RS approaches
  • Evaluation methods for RS
  • Ethical issues in RS
  • Applications of RS and HAII (e.g., entertainment, healthcare, education, finance, etc.)

Learning Outcomes

Subject-specific Knowledge:
  • Key concepts and principles underpinning Human-AI Interaction (HAII) and their implications for user experience (UX) and usability, including affective and cognitive factors.
  • An understanding of the different types of recommender system techniques, their purpose, domains of application, usage and evaluation.
Subject-specific Skills:
  • An ability to design and evaluate interactive AI systems.
  • An ability to critically assess trust and trustworthiness in autonomous and intelligent systems.
  • An ability to integrate ethical and responsible AI frameworks into the design and evaluation of Human-AI systems.
  • An ability to design, implement and evaluate a personalised recommender system for a specific domain.
Key Skills:
  • An ability to propose AI solutions to real-world problems.
  • An ability to critically analyse and evaluate ethical issues, current practices and recent advances in AI.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

  • Lectures enable students to learn new materials relevant to Applications of AI.
  • The Assignment is a Data Design Template which will involve designing a structured record template and collecting a sample dataset using it. The Report is a Data Analysis Report which will involve conducting an in-depth analysis of a larger dataset to present key findings, interpretations, and evidence-based conclusions for a specific HAII topic.
  • The Presentation assesses knowledge in the threshold RS concepts and skills in applying RS techniques and methods by designing, developing and evaluating AI systems that deliver personalised recommendations.

Teaching Methods and Learning Hours

Activity Number Frequency Duration Total/Hours Attendance Monitored
Lectures 40 2 per week 1 hour 40
Preparation and Reading 160
Total 200

Summative Assessment

Component: Coursework Component Weighting: 100%
Element Length / duration Element Weighting Resit Opportunity
Assignment 10%
Report 40%
Presentation 50%

Formative Assessment:

Example formative exercises are given during the course.


Students who do not attend monitored activities shown under Teaching Methods and Learning Hours, or who fail to complete the summative or formative assessment(s) specified above, may be subject to the Academic Progress procedures defined in the University's General Regulation V, and may be required to leave the University.