add survey data

Author: MootezSaaD

README.md

@@ -19,21 +19,22 @@ Researchers in the field may use and build upon the proposed approach for variab
 
 ### Project Structure
 
-1. `data`: Contains scripts related to data handling. This includes downloading raw data and creating the training and test datasets:  
+1. `data`: Contains scripts related to data handling. This includes downloading raw data and creating the training and test datasets (RQ1, RQ2 and RQ3):  
     - `SelectedRepositories.csv`: CSV file containing the repositories that were selected based on the criteria mentioned in the manuscript.  
     - `repos_download.py`: a script used to download repositories as zip files, extract their content, and copy all `.java` files in the specified directory.  
     - `dataset_creation.py`: converts raw data generated by `repos_download.py` into CSV files for training and testing, respectively.
     - `training`: contains the training dataset stored in CSV files that we generated.
     - `testing`: contains the CSV file of the testing dataset that we generated.
+    - `survey_data`: contains the Excel sheets of the raw survey responses and the aggregated version from which we generate the results of RQ3. The original survey can be accessed through this [link](https://forms.office.com/pages/responsepage.aspx?id=mRm4YH8LLUGSo-F9iunj4HbSH6eNn6hEr16DyJ7J0iVUMjMxV01ZNjZCME81NFUzVzhVUVZESE4yNS4u).
 
-2. `training`: Contains scripts used to train the model using the method described in the manuscript:
+2. `training`: Contains scripts used to train the model using the method described in the manuscript (RQ1 and RQ2):
     - `variable_predictor.py`: script used to train the model.
 
-3. `evaluation`: Contains scripts used to train the model using the method described in the manuscript:
+3. `evaluation`: Contains scripts used to train the model using the method described in the manuscript (RQ1 and RQ2):
     - `model_eval.py`: script used to evaluate the model.
     - `ChatGPT_identifiers.py`: script used to run experiments that involve GPT4 mentioned in the manuscript.
 
-4. `survey_codes`: Contains the code snippets that were used in the survey described in the manuscript.
+4. `survey_codes`: Contains the code snippets that were used in the survey described in the manuscript (RQ3).
 
 5. `figures`: Contains figures that are displayed in the README.