File size: 1,155 Bytes
7eea29a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 |
from sentence_transformers import SentenceTransformer, util
# Load pre-trained model once
model = SentenceTransformer('all-MiniLM-L6-v2')
def check_plagiarism(text1, text2, threshold=0.8):
"""
Compare two texts and return similarity score and verdict.
Parameters:
text1 (str): First text (e.g., student answer)
text2 (str): Second text (e.g., source material)
threshold (float): Similarity threshold (default = 0.8)
Returns:
result (str): Similarity percentage and plagiarism verdict.
"""
try:
embedding1 = model.encode(text1, convert_to_tensor=True)
embedding2 = model.encode(text2, convert_to_tensor=True)
similarity_score = util.cos_sim(embedding1, embedding2).item()
similarity_percent = round(similarity_score * 100, 2)
if similarity_score >= threshold:
verdict = "⚠️ Potential Plagiarism"
else:
verdict = "✅ No Significant Plagiarism Detected"
return f"Similarity: {similarity_percent}%\nResult: {verdict}"
except Exception as e:
return f"Error during plagiarism check: {str(e)}"
|