Paper 2: Combined internal assessment (project)

Project brief: Product review sentiment classifier

A small online shop receives hundreds of customer reviews and wants to spot unhappy customers quickly. Build an AI system that classifies a written review as positive or negative. Starter reviews:

Review	Label
"Arrived quickly and works perfectly"	positive
"Broke after two days, really disappointed"	negative
"Great value, would buy again"	positive
"Terrible customer service, never again"	negative
"Love it! Exactly as described"	positive
"The size was wrong and the refund took weeks"	negative
"Not bad at all, actually really good"	positive
"Oh great, another charger that doesn't charge"	negative

Requirements: - collect at least 40 labelled reviews in total (you may write realistic ones) - train and test a classifier, or build a keyword-scoring system and compare it with a trained model - flag negative reviews for a human to reply to Suggested tools: Teachable Machine is not suitable for text – use Python, a beginner text-classification tool, or a keyword-scoring spreadsheet.

1(a)3 marks

Describe the problem your AI system will solve and who will use it.

1(b)4 marks

Write four success criteria for your system. Each criterion must be specific and measurable.

1(c)4 marks

Identify the AI technique you will use. Justify your choice and explain why one alternative technique would be less suitable.

2(a)6 marks

Produce a design for your system. Use a flowchart, pseudocode, decision tree or labelled system diagram (described in words if needed). Show the inputs, processing and outputs.

2(b)4 marks

Describe your data plan: what data you need, where it will come from, how much you need and (if relevant) the features and labels.

3(a)5 marks

Describe how you collected and prepared your data so that it was clean and correctly structured. Give specific examples of problems you found and how you fixed them.

3(b)2 marks

Explain how you separated data for training and testing, and why.

49 marks

Describe how you built your AI system. Include key code, rules or screenshots (described in words) as evidence, and explain how each part works.

5(a)6 marks

Create a test plan for your system with at least five tests. For each test give the input/test data, the type of test (normal, boundary or unexpected), the expected result and the actual result.

5(b)4 marks

Record the overall performance of your system on the test data and interpret the results. Show any calculations.

6(a)6 marks

Evaluate your system against each of your success criteria, using evidence from your testing.

6(b)4 marks

Explain the ethical, privacy or bias issues that could arise if your system were used for real, and how you would reduce them.

6(c)3 marks

Suggest three improvements to your system. For each, explain how it would improve the system.

Finished?

Answer every question to finish (13 left), or finish when the time’s up.

Score 0 / 60 · 0 of 13 marked

This paper is written by Plasmo in the style of the LRN GCSE Artificial Intelligence exam. It is not a past paper and is not produced or endorsed by the exam board.

LRN GCSE Artificial Intelligence Mock Exam: Paper 2: Combined internal assessment (project) (Mock F) | Plasmo