![]() ![]() Souce code: experiments.py listed in the Code section.Methods: (1) Tokenization, (2) Stop words removal, and (3) Stemming. ![]() Output: The pre-processed training dataset.Input: Training database (Data item 1).Using dic training data for classifier.xlsxĬomprises original training dataset (data item 1) and unseen but QA and AT relevant terms of the trained dictionary (date item 4). You may also use the free 14-day trial version of MAXQDA 2020, which is available at for download.Ĭomprises the binary classification results of six machine learning methods.Ĭomprises the architectural posts for dictionary training that crawled from Stack Overflow. The file can be opened by MAXQDA 2020, which are available at for download. Particularly, the relationships between ATs and QAs can be found in the group named "ATs->QAs" in the coding results. We analyzed and coded the considerations discussed in QA-AT posts and the relationships between QAs and ATs. QA-AT posts labelling and encoding.mx20 is the results of QA-AT posts labelling and encoding that were analyzed by the MAXQDA tool. QAs are used for eight high-level QAs identification,Īnd QA related terms are used for dictionary training.Ĭomprises the sensitive terms of QAs and ATs in the dictionary trained by the 1741 architectural posts. AT names are used for searching QA-AT posts,Īnd AT related terms are used for dictionary training.Ĭomprises QAs and their related terms. Training data for classifier.xlsx comprises 1165 QA-AT posts (with URL links) and 1200 non QA-AT posts collected from Stack Overflow.Ĭomprises AT names and their related terms. Data items and results of the experiment and data analysis: ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |