Highlight Similar text in a document using NLP in Python

Question

I want to build an AI agent which could highlight similar text among 2 or 3 different students. For getting similarity between documents, I am using this code (from a Medium article)

student_files = [doc for doc in os.listdir() if doc.endswith('.txt')]
student_notes = [open(_file, encoding='utf-8').read()
                 for _file in student_files]

def vectorize(Text): return TfidfVectorizer().fit_transform(Text).toarray()
def similarity(doc1, doc2): return cosine_similarity([doc1, doc2])


vectors = vectorize(student_notes)
s_vectors = list(zip(student_files, vectors))
plagiarism_results = set()


def check_plagiarism():
    global s_vectors
    for student_a, text_vector_a in s_vectors:
        print(student_a)
        new_vectors = s_vectors.copy()
        current_index = new_vectors.index((student_a, text_vector_a))
        del new_vectors[current_index]
        for student_b, text_vector_b in new_vectors:
            sim_score = similarity(text_vector_a, text_vector_b)[0][1]
            student_pair = sorted((student_a, student_b))
            score = (student_pair[0], student_pair[1], sim_score)
            plagiarism_results.add(score)
    return plagiarism_results


for data in check_plagiarism():
    print(data)

I am also aware that python has a package named docx which is used for various actions like highlighting, formatting etc. But I am unable to combine the two. I don't want to make a just basic similar common word highlighting but want something that could highlight the whole area of similar wordings. Any help on how to go about it would be appreciated.