Evaluation of subjective answers using semantic simmilarity
Objective answers can be easily checked but checking subjective answers requires understanding the context and the meaning of the words. Two answers, conveying the same idea, can be written quite differently. The checking of subjective answers requires human intelligence and effort. We propose an au
2025-06-28 16:32:27 - Adil Khan
Evaluation of subjective answers using semantic simmilarity
Project Area of Specialization Computer ScienceProject SummaryObjective answers can be easily checked but checking subjective answers requires understanding the context and the meaning of the words. Two answers, conveying the same idea, can be written quite differently. The checking of subjective answers requires human intelligence and effort. We propose an automatic answer checker application that checks and marks written answers almost similar to a human being. This software application is built to check subjective answers and allocate marks to the user after verifying the answer. The system requires you to store the original answer for the system. This facility is provided to the admin. The admin may insert questions and respective subjective answers in the system. These answers are stored as text files. Once the user enters his/her answers the system then compares this answer with the original answer provided by the admin and allocates marks accordingly. Different NLP techniques will be used for this purpose. The system based on artificial intelligence will verify which technique is best for which type of question and allocate marks accordingly.
Project ObjectivesAn automatic evaluation system that evaluates the examination for reducing human work.
Project Implementation MethodThe project will be implemented using different models and similarity techniques. A big part of the project’s code will be written in python. Initially, the answers, in the form of text files, will be analyzed using NLP techniques.
Benefits of the Project1) Reduction in the evaluator’s workload.
2) Uniformity in the checking of all answers.
3) Reduce unbiasedness in paper checking.
Technical Details of Final DeliverableWe take input in text form and gave the result according to the defined points of the instructor.
We will provide the tutor’s answer and answer of students as input and the evaluated result will be shown as output.
Final Deliverable of the Project Software SystemCore Industry ITOther Industries Education Core Technology OthersOther Technologies Artificial Intelligence(AI)Sustainable Development Goals Quality EducationRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 80000 | |||
| For model training ZOTAC GAMING GeForce RTX 30 Series | Equipment | 1 | 70000 | 70000 |
| Data gathering | Miscellaneous | 1 | 10000 | 10000 |