Presentation
-
Upload
sonam05 -
Category
Engineering
-
view
76 -
download
1
description
Transcript of Presentation
![Page 1: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/1.jpg)
Presented bySonam (10103470)
![Page 2: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/2.jpg)
Stack Overflow is a question andanswer site for professional andenthusiast programmers.
![Page 3: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/3.jpg)
Tags are user-generated labels/keywords
for entities that summarize the features of
the questions from different views
![Page 4: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/4.jpg)
Questions that are not related to programming
topics are marked ‘closed’ by experienced users
and community moderators
![Page 5: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/5.jpg)
Questions that are
deleted/locked by
experienced users and
community
moderators
![Page 6: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/6.jpg)
•Tag recommendation to questions being posted on Stack Overflow
•Prediction of ‘closed’ question at post creation time
•Prediction of ‘deleted’ question after deletion
![Page 7: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/7.jpg)
•Easier question posting
•Better organization of the site
![Page 8: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/8.jpg)
•Feedback to question asker
•Community moderator assistance
![Page 9: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/9.jpg)
•Feedback to Moderator/owner
•Whether it should worth deletion or remain undeleted
![Page 10: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/10.jpg)
![Page 11: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/11.jpg)
![Page 12: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/12.jpg)
Database Snapshot
![Page 13: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/13.jpg)
![Page 14: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/14.jpg)
•TF.IDF WEIGHTING•NAÏVE BAYES CLASSIFICATION•SVM CLASSIFICATION•K- NEAREST NEIGHBOR CLASSIFICATION
![Page 15: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/15.jpg)
•Flow chart of tag prediction
![Page 16: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/16.jpg)
Following graph shows the comparison of accuracy with andwithout feedback.
![Page 17: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/17.jpg)
Represents accuracies corresponding to each post for therecommendation of 1 tag,2 tags, top 3, top 4, and top5 tags
![Page 18: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/18.jpg)
Accuracies of full system for Tag reccomending system with the variation of tags
![Page 19: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/19.jpg)
![Page 20: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/20.jpg)
•RANDOM FOREST CLASSIFIER•ADABOOST CLASSIFIER•EXTRATREES CLASSIFIER
![Page 21: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/21.jpg)
•Score of post• User’s reputation• Age of user account• Score of other posts of user• Post content
![Page 22: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/22.jpg)
•Flow chart of Closed Question
![Page 23: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/23.jpg)
Graph shows the importance of different features basis on Random Forest
![Page 24: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/24.jpg)
Graph shows the importance of different features basis on AdaBoost
![Page 25: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/25.jpg)
Graph shows the importance of different features basis on ExtraTrees
![Page 26: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/26.jpg)
Following graph shows the comparison of accuracy with different number of features
![Page 27: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/27.jpg)
Following graph shows the comparison of accuracy with different number of estimators
![Page 28: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/28.jpg)
Comparison between three classifiers
On the basis of closed question found:
![Page 29: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/29.jpg)
Accuracy comparison:
On the basis of estimators:
![Page 30: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/30.jpg)
Accuracy comparison:
On the basis of changing training set count :
![Page 31: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/31.jpg)
![Page 32: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/32.jpg)
•RANDOM FOREST CLASSIFIER•ADABOOST CLASSIFIER•EXTRATREES CLASSIFIER
![Page 33: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/33.jpg)
•Score of post• User’s reputation• Age of user account• Score of other posts of user• Post content
![Page 34: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/34.jpg)
•Flow chart of Deletion
![Page 35: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/35.jpg)
Though deleted questions are mostly on relevant. These are removed by reputed
authors which do this for saving their reputation on stack overflow.
![Page 36: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/36.jpg)
Accuracy comparison:
On the basis of estimators:
![Page 37: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/37.jpg)
Accuracy comparison:
On the basis of changing training set count :
![Page 38: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/38.jpg)
•Tag recommendation has been implemented with and without feedback. We found that we achieve better accuracy with feedback.
•‘Closed’ question prediction has been implemented with three different classifiers and along with different number of features and estimators. We found that we achieve better accuracy in Adaboost.
•Same for deleted questions we found with all three classifiers and resulted that many questions are worth deletion but some require to get back.
![Page 39: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/39.jpg)
• Increase the accuracy of our algorithms.
• Predicting the trend on stack overflow.
•Predicting & finding the unanswered question.
•Predict the quality of answers with non textual features.
![Page 40: Presentation](https://reader035.fdocuments.net/reader035/viewer/2022081401/559a8ade1a28ab684d8b468b/html5/thumbnails/40.jpg)