Skip to content

Data Science Final Year Topic: Evaluation of Product Review Rating-Text Mismatch

This Data Science final year project investigates identifying reviews whose written sentiment differs from their numerical rating, with explicit data definitions and reproducible analysis rather than invented findings.

Why choose this project topic?

This topic turns identifying reviews whose written sentiment differs from their numerical rating into a measurable analytical question. Comparing mismatch precision, recall and annotation agreement gives a student material for visual results, methodological criticism and a discussion of how the data's limitations change the conclusion.

How does product review rating-text mismatch affect identifying reviews whose written sentiment differs from their numerical rating, as measured by mismatch precision, recall and annotation agreement?

Choose an accessible licensed or synthetic dataset, agree the unit of analysis and narrow identifying reviews whose written sentiment differs from their numerical rating to a reproducible comparison your supervisor can review.

Proposed project objectives

  1. 01Define the data, assumptions and comparison design for identifying reviews whose written sentiment differs from their numerical rating.
  2. 02Use licensed review text, create a reviewed mismatch subset and compare rule-based and statistical detection while retaining ambiguous examples.
  3. 03Compare mismatch precision, recall and annotation agreement and report uncertainty and sensitivity to analytical choices.

A suggested research approach

Use licensed review text, create a reviewed mismatch subset and compare rule-based and statistical detection while retaining ambiguous examples. Confirm the data licence and variable definitions before analysis. Preserve an untouched evaluation set where relevant, document exclusions and missingness, and report mismatch precision, recall and annotation agreement with uncertainty or sensitivity checks rather than selecting only favourable results.

What you will need

  • Licensed review corpus
  • Mismatch coding guide
  • Text analysis environment

Keep your project scope clear

Mismatch does not prove a review is fraudulent or that a customer acted dishonestly.

Data Science project chapter outline

Use this outline as a starting point. You can edit the chapter titles to match your department’s format during setup.

  1. Chapter 1Introduction
  2. Chapter 2Literature Review
  3. Chapter 3Research Methodology
  4. Chapter 4Presentation and Analysis of Results
  5. Chapter 5Summary, Conclusion and Recommendations

Turn this topic into your own final year project.

Your title, department, research question and outline are ready. Add your institution, personalise the details and continue to your project workspace.

Generate the Complete Project Generation uses your word balance. Review the draft and supply your own verified research findings.