Student Assignment Plagiarism Detection
Semester Project (2021-2022)
Department of Computer Science
Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad
Introduction
Plagiarism detection or text similarity
detection is the process of locating instances
of plagiarism and/or copyright violation
within a work or document. Human
detection is the most traditional form of
identifying plagiarism from written work.
This can be a lengthy and time-consuming
task for the reader and can also result in
inconsistencies in how plagiarism is
identified within an organization. As we
know that technology evolution is getting
fast day by day, so people are getting more
dependent on technology.It is very difficult
for teachers to read assignments of all
student and then figure it out that a specific
student’s assignment is copied by other
students. To overcome this difficulty,
plagiarism detection is a best technique in
checking similarity.
.
Motivations &
Objectives
i. Helpful in online classroom .
ii. Students can submit their
assignments rather than handwritten
iii. Calculates the text similarity
percentage of all students and show
result to the teacher and students as
well.
iv. Familiarity with natural language
processing and text mining
v. Familiarity with different text
similarity detection algorithms.
vi. Reduce time and Efforts of teachers
to mark assignments because they
have calculated similarity index
given by application.
Literature Review
The data request and response idea in VANET is introduced by
[12], which is traditionally IP-based LTE-V communication.
This approach introduced the pre-fetching of the data context
for the VANET environment. Cooperative and non-
cooperative caching are introduced with the high availability
of the nodes for effective communication. In non-
cooperative, all nodes share non-caching information [13],
whereas cooperative nodes share cached information to
reduce the redundancy in caching and delay access[14-17].
Group-based V2V communication is introduced in [20], using
a Group-based leader and other communication members.
Proposed Architecture/
Solution
Ar
Results
Admin Application
To manage reports and see the results.
Group Members
Asa Bibi, Registration #
emaiil@gmail.com
Asa Bibi, Registration #
emaiil@gmail.com
Supervisor by:
Dr. Muhammad Munwar Iqbal
Department of Computer Science , SZABIST, Islamabad Campus , Islamabad
.Solution Details/ Description
The proposed framework in Figure 3.1 defines the
steps of sentiment Analysis. First step is collection
of Datasets and after collection of datasets, pre-
process of these datasets will be performed.
Afterwards feature engineering of these processed
datasets will be performed using equations shown
in section 3.2. After extracting features from these
pre-processed data sets, these extracted features are
fed to different classifiers for classifying them in
classes. After classification next step is
quantification of dataset.
Conclusion
Student Assignment plagiarism Detection is
a great application and has a great scope.
Through this web application user feels a
lot easier and comfortable. We have used
advanced technology for developing this
application and try to provide a comfort
zone to both teacher and student. It will
save time of both teacher and student.
Student can easily submit their
assignments and teacher can easily find
out plagiarism among the assignments.
And we are familiar with different
plagiarism detection algorithms.
User Application
Student/teacher can sign up and login.
Future Directions
Further modules will be added with the
passage of time which will make this
application more useful. With the help of
user’s feedback, we will add those modules
which the users need. In future work live
streaming can be added.
Figure7:CacheHitRatiooverNodeSize150

PROJECT POSTER TEM.pptx

  • 1.
    Student Assignment PlagiarismDetection Semester Project (2021-2022) Department of Computer Science Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad Introduction Plagiarism detection or text similarity detection is the process of locating instances of plagiarism and/or copyright violation within a work or document. Human detection is the most traditional form of identifying plagiarism from written work. This can be a lengthy and time-consuming task for the reader and can also result in inconsistencies in how plagiarism is identified within an organization. As we know that technology evolution is getting fast day by day, so people are getting more dependent on technology.It is very difficult for teachers to read assignments of all student and then figure it out that a specific student’s assignment is copied by other students. To overcome this difficulty, plagiarism detection is a best technique in checking similarity. . Motivations & Objectives i. Helpful in online classroom . ii. Students can submit their assignments rather than handwritten iii. Calculates the text similarity percentage of all students and show result to the teacher and students as well. iv. Familiarity with natural language processing and text mining v. Familiarity with different text similarity detection algorithms. vi. Reduce time and Efforts of teachers to mark assignments because they have calculated similarity index given by application. Literature Review The data request and response idea in VANET is introduced by [12], which is traditionally IP-based LTE-V communication. This approach introduced the pre-fetching of the data context for the VANET environment. Cooperative and non- cooperative caching are introduced with the high availability of the nodes for effective communication. In non- cooperative, all nodes share non-caching information [13], whereas cooperative nodes share cached information to reduce the redundancy in caching and delay access[14-17]. Group-based V2V communication is introduced in [20], using a Group-based leader and other communication members. Proposed Architecture/ Solution Ar Results Admin Application To manage reports and see the results. Group Members Asa Bibi, Registration # emaiil@gmail.com Asa Bibi, Registration # emaiil@gmail.com Supervisor by: Dr. Muhammad Munwar Iqbal Department of Computer Science , SZABIST, Islamabad Campus , Islamabad .Solution Details/ Description The proposed framework in Figure 3.1 defines the steps of sentiment Analysis. First step is collection of Datasets and after collection of datasets, pre- process of these datasets will be performed. Afterwards feature engineering of these processed datasets will be performed using equations shown in section 3.2. After extracting features from these pre-processed data sets, these extracted features are fed to different classifiers for classifying them in classes. After classification next step is quantification of dataset. Conclusion Student Assignment plagiarism Detection is a great application and has a great scope. Through this web application user feels a lot easier and comfortable. We have used advanced technology for developing this application and try to provide a comfort zone to both teacher and student. It will save time of both teacher and student. Student can easily submit their assignments and teacher can easily find out plagiarism among the assignments. And we are familiar with different plagiarism detection algorithms. User Application Student/teacher can sign up and login. Future Directions Further modules will be added with the passage of time which will make this application more useful. With the help of user’s feedback, we will add those modules which the users need. In future work live streaming can be added. Figure7:CacheHitRatiooverNodeSize150