Evaluating Privacy Questions From Stack Overflow: Can ChatGPT Compete?

被引:3
|
作者
Defile, Zack [1 ]
Radel, Sean [1 ]
Godinez, Joe [1 ]
Engstrom, Garrett [1 ]
Brucker, Theo [1 ]
Young, Kenzie [1 ]
Ghanavati, Scpideh [1 ]
机构
[1] Univ Maine, Sch Comp & Informat Sci, Orono, ME 04469 USA
关键词
privacy; analysts; Stack Overflow; ChatGPT;
D O I
10.1109/REW57809.2023.00048
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Stack Overflow and other similar forums are commonly used by developers to seek answers for their software development as well as privacy-related concerns. Recently, ChatGPT has been used as an alternative to generate code or produce responses to developers' questions. In Ibis paper, we aim to understand developers' privacy challenges by evaluating the types of privacy-related questions asked on Stack Overflow. We then conduct a comparative analysis between the accepted responses given by Stack Overflow users and the responses produced by ChatGPT for those extracted questions to identify if ChatGPT could serve as a viable alternative. Our results show that most privacy-related questions are related to choice/consent, aggregation, and identification. Furthermore, our findings illustrate that ChatGPT generates similarly correct responses for about 56% of questions while for the rest of the responses, the answers from Stack Overflow are slightly more accurate than ChatGPT.
引用
收藏
页码:239 / 244
页数:6
相关论文
共 50 条
  • [31] A Discriminative Model Approach for Suggesting Tags Automatically for Stack Overflow Questions
    Saha, Avigit K.
    Saha, Ripon K.
    Schneider, Kevin A.
    2013 10TH IEEE WORKING CONFERENCE ON MINING SOFTWARE REPOSITORIES (MSR), 2013, : 73 - 76
  • [32] An Observational Study on Flask Web Framework Questions on Stack Overflow (SO)
    Albesher, Luluh
    Alfayez, Reem
    IET SOFTWARE, 2024, 2024
  • [33] Evaluating the performance of ChatGPT in answering questions related to urolithiasis
    Hakan Cakir
    Ufuk Caglar
    Oguzhan Yildiz
    Arda Meric
    Ali Ayranci
    Faruk Ozgor
    International Urology and Nephrology, 2024, 56 : 17 - 21
  • [34] Evaluating the performance of ChatGPT in answering questions related to urolithiasis
    Cakir, Hakan
    Caglar, Ufuk
    Yildiz, Oguzhan
    Meric, Arda
    Ayranci, Ali
    Ozgor, Faruk
    INTERNATIONAL UROLOGY AND NEPHROLOGY, 2024, 56 (01) : 17 - 21
  • [35] A study on classifying Stack Overflow questions based on difficulty by utilizing contextual features
    Raida, Maliha Noushin
    Sristy, Zannatun Naim
    Ulfat, Nawshin
    Monisha, Sheikh Moonwara Anjum
    Mostafa, Md. Jubair Ibna
    Haque, Md. Nazmul
    JOURNAL OF SYSTEMS AND SOFTWARE, 2024, 208
  • [36] Evaluating the psychometric properties of ChatGPT-generated questions
    Bhandari, Shreya
    Liu, Yunting
    Kwak, Yerin
    Pardos, Zachary A.
    Computers and Education: Artificial Intelligence, 2024, 7
  • [37] How Developers and Tools Categorize Sentiment in Stack Overflow Questions - A Pilot Study
    Mansoor, Niloofar
    Peterson, Cole S.
    Sharif, Bonita
    2021 IEEE/ACM SIXTH INTERNATIONAL WORKSHOP ON EMOTION AWARENESS IN SOFTWARE ENGINEERING SEMOTION 2021, 2021, : 19 - 22
  • [38] Quality Questions Need Quality Code: Classifying Code Fragments on Stack Overflow
    Duijn, Maarten
    Kucera, Adam
    Bacchelli, Alberto
    12TH WORKING CONFERENCE ON MINING SOFTWARE REPOSITORIES (MSR 2015), 2015, : 410 - 413
  • [39] Do Subjectivity and Objectivity Always Agree? A Case Study with Stack Overflow Questions
    Mondal, Saikat
    Rahman, Mohammad Masudur
    Roy, Chanchal K.
    2023 IEEE/ACM 20TH INTERNATIONAL CONFERENCE ON MINING SOFTWARE REPOSITORIES, MSR, 2023, : 389 - 401
  • [40] SCC plus plus : Predicting the programming language of questions and snippets of Stack Overflow
    Alrashedy, Kamel
    Dharmaretnam, Dhanush
    German, Daniel M.
    Srinivasan, Venkatesh
    Gulliver, T. Aaron
    JOURNAL OF SYSTEMS AND SOFTWARE, 2020, 162