This artifact accompanies the SEET@ICSE article "Assessing the impact of hints in learning formal specification", which reports on a user study to investigate the impact of different types of automated hints while learning a formal specification language, both in terms of immediate performance and learning retention, but also in the emotional response of the students. This research artifact provides all the material required to replicate this study (except for the proprietary questionnaires passed to assess the emotional response and user experience), as well as the collected data and data analysis scripts used for the discussion in the paper.

Dataset

The artifact contains the resources described below.

Experiment resources

The resources needed for replicating the experiment, namely in directory experiment:

alloy_sheet_pt.pdf: the 1-page Alloy sheet that participants had access to during the 2 sessions of the experiment. The sheet was passed in Portuguese due to the population of the experiment.

alloy_sheet_en.pdf: a version the 1-page Alloy sheet that participants had access to during the 2 sessions of the experiment translated into English.

docker-compose.yml: a Docker Compose configuration file to launch Alloy4Fun populated with the tasks in directory data/experiment for the 2 sessions of the experiment.

api and meteor: directories with source files for building and launching the Alloy4Fun platform for the study.

Experiment data

The task database used in our application of the experiment, namely in directory data/experiment:

Model.json, Instance.json, and Link.json: JSON files with to populate Alloy4Fun with the tasks for the 2 sessions of the experiment.

identifiers.txt: the list of all (104) available participant identifiers that can participate in the experiment.

Collected data

Data collected in the application of the experiment as a simple one-factor randomised experiment in 2 sessions involving 85 undergraduate students majoring in CSE. The experiment was validated by the Ethics Committee for Research in Social and Human Sciences of the Ethics Council of the University of Minho, where the experiment took place. Data is shared the shape of JSON and CSV files with a header row, namely in directory data/results:

data_sessions.json: data collected from task-solving in the 2 sessions of the experiment, used to calculate variables productivity (PROD1 and PROD2, between 0 and 12 solved tasks) and efficiency (EFF1 and EFF2, between 0 and 1).

data_socio.csv: data collected from socio-demographic questionnaire in the 1st session of the experiment, namely:

participant identification: participant's unique identifier (ID);

socio-demographic information: participant's age (AGE), sex (SEX, 1 through 4 for female, male, prefer not to disclosure, and other, respectively), and average academic grade (GRADE, from 0 to 20, NA denotes preference to not disclosure).

data_emo.csv: detailed data collected from the emotional questionnaire in the 2 sessions of the experiment, namely:

participant identification: participant's unique identifier (ID) and the assigned treatment (column HINT, either N, L, E or D);

detailed emotional response data: the differential in the 5-point Likert scale for each of the 14 measured emotions in the 2 sessions, ranging from -5 to -1 if decreased, 0 if maintained, from 1 to 5 if increased, or NA denoting failure to submit the questionnaire. Half of the emotions are positive (Admiration1 and Admiration2, Desire1 and Desire2, Hope1 and Hope2, Fascination1 and Fascination2, Joy1 and Joy2, Satisfaction1 and Satisfaction2, and Pride1 and Pride2), and half are negative (Anger1 and Anger2, Boredom1 and Boredom2, Contempt1 and Contempt2, Disgust1 and Disgust2, Fear1 and Fear2, Sadness1 and Sadness2, and Shame1 and Shame2). This detailed data was used to compute the aggregate data in data_emo_aggregate.csv and in the detailed discussion in Section 6 of the paper.

data_umux.csv: data collected from the user experience questionnaires in the 2 sessions of the experiment, namely:

participant identification: participant's unique identifier (ID);

user experience data: summarised user experience data from the UMUX surveys (UMUX1 and UMUX2, as a usability metric ranging from 0 to 100).

participants.txt: the list of participant identifiers that have registered for the experiment.

Analysis scripts

The analysis scripts required to replicate the analysis of the results of the experiment as reported in the paper, namely in directory analysis:

analysis.r: An R script to analyse the data in the provided CSV files; each performed analysis is documented within the file itself.

requirements.r: An R script to install the required libraries for the analysis script.

normalize_task.r: A Python script to normalize the task JSON data from file data_sessions.json into the CSV format required by the analysis script.

normalize_emo.r: A Python script to compute the aggregate emotional response in the CSV format required by the analysis script from the detailed emotional response data in the CSV format of data_emo.csv.

Dockerfile: Docker script to automate the analysis script from the collected data.

Setup

To replicate the experiment and the analysis of the results, only Docker is required.

If you wish to manually replicate the experiment and collect your own data, you'll need to install:

A modified version of the Alloy4Fun platform, which is built in the Meteor web framework. This version of Alloy4Fun is publicly available in branch study of its repository at https://github.com/haslab/Alloy4Fun/tree/study.

If you wish to manually replicate the analysis of the data collected in our experiment, you'll need to install:

Python to manipulate the JSON data collected in the experiment. Python is freely available for download at https://www.python.org/downloads/, with distributions for most platforms.

R software for the analysis scripts. R is freely available for download at https://cran.r-project.org/mirrors.html, with binary distributions available for Windows, Linux and Mac.

Usage

Experiment replication

This section describes how to replicate our user study experiment, and collect data about how different hints impact the performance of participants.

To launch the Alloy4Fun platform populated with tasks for each session, just run the following commands from the root directory of the artifact. The Meteor server may take a few minutes to launch, wait for the "Started your app" message to show.

cd experimentdocker-compose up

This will launch Alloy4Fun at http://localhost:3000. The tasks are accessed through permalinks assigned to each participant. The experiment allows for up to 104 participants, and the list of available identifiers is given in file identifiers.txt. The group of each participant is determined by the last character of the identifier, either N, L, E or D. The task database can be consulted in directory data/experiment, in Alloy4Fun JSON files.

In the 1st session, each participant was given one permalink that gives access to 12 sequential tasks. The permalink is simply the participant's identifier, so participant 0CAN would just access http://localhost:3000/0CAN. The next task is available after a correct submission to the current task or when a time-out occurs (5mins). Each participant was assigned to a different treatment group, so depending on the permalink different kinds of hints are provided. Below are 4 permalinks, each for each hint group:

Group N (no hints): http://localhost:3000/0CAN

Group L (error locations): http://localhost:3000/CA0L

Group E (counter-example): http://localhost:3000/350E

Group D (error description): http://localhost:3000/27AD

In the 2nd session, likewise the 1st session, each permalink gave access to 12 sequential tasks, and the next task is available after a correct submission or a time-out (5mins). The permalink is constructed by prepending the participant's identifier with P-. So participant 0CAN would just access http://localhost:3000/P-0CAN. In the 2nd sessions all participants were expected to solve the tasks without any hints provided, so the permalinks from different groups are undifferentiated.

Before the 1st session the participants should answer the socio-demographic questionnaire, that should ask the following information: unique identifier, age, sex, familiarity with the Alloy language, and average academic grade.

Before and after both sessions the participants should answer the standard PrEmo 2 questionnaire. PrEmo 2 is published under an Attribution-NonCommercial-NoDerivatives 4.0 International Creative Commons licence (CC BY-NC-ND 4.0). This means that you are free to use the tool for non-commercial purposes as long as you give appropriate credit, provide a link to the license, and do not modify the original material. The original material, namely the depictions of the diferent emotions, can be downloaded from https://diopd.org/premo/. The questionnaire should ask for the unique user identifier, and for the attachment with each of the depicted 14 emotions, expressed in a 5-point Likert scale.

After both sessions the participants should also answer the standard UMUX questionnaire. This questionnaire can be used freely, and should ask for the user unique identifier and answers for the standard 4 questions in a 7-point Likert scale. For information about the questions, how to implement the questionnaire, and how to compute the usability metric ranging from 0 to 100 score from the answers, please see the original paper:

Kraig Finstad. 2010. The usability metric for user experience. Interacting with computers 22, 5 (2010), 323–327.

Analysis of other applications of the experiment

This section describes how to replicate the analysis of the data collected in an application of the experiment described in Experiment replication.

The analysis script expects data in 4 CSV files,

This is a dataset of spectrogram images created from the train_spectrograms parquet data from the Harvard Medical School Harmful Brain Activity Classification competition. The parquet files have been transformed with the following code, referencing the HMS-HBAC: KerasCV Starter Notebook

def process_spec(spec_id, split="train"):
  # read the data
  data = pd.read_parquet(path/f'{split}_spectrograms'/f'{spec_id}.parquet')
  
  # read the label
  label = unique_df[unique_df.spectrogram_id == spec_id]["target"].item()
  
  # replace NA with 0
  data = data.fillna(0)
  
  # convert DataFrame to array
  data = data.values[:, 1:]
  
  # transpose
  data = data.T
  data = data.astype("float32")
  
  # clip data to avoid 0s
  data = np.clip(data, math.exp(-4), math.exp(8))

  # take log data to magnify differences
  data = np.log(data)

  # normalize data
  data=(data-data.mean())/data.std() + 1e-6

  # convert to 3 channels
  data = np.tile(data[..., None], (1, 1, 3))
  
  # convert array to PILImage
  im = PILImage.create(Image.fromarray((data * 255).astype(np.uint8)))
  im.save(f"{SPEC_DIR}/{split}_spectrograms/{label}/{spec_id}.png")

This dataset provides the following data and code:The original data collected from FAO, USDA and UN to assess the national food security of the G20 members.The python code to normalize the raw data and calculate the weighted sum of the eight indicators.The patent and vulnerability data and the code of cluster analysis.The data of chemical use and the code of Entropy Weight Method.The python code to visualize the bar plot and radar plots.

3.4 hours of audio synthesized using the open-source Surge synthesizer, based upon 2084 presets included in the Surge package. These represent ``natural'' synthesis sounds---i.e.presets devised by humans.

We generated 4-second samples playing at velocity 64 with a note-on duration of 3 seconds. For each preset, we varied only the pitch, from MIDI 21--108, the range of a grand piano. Every sound in the dataset was RMS-level normalized using the normalize package. There was no elegant way to dedup this dataset; however only a small percentage of presets (like drums and sound effects) had no perceptual pitch variation or ordering.

We used the Surge Python API to generate this dataset.

Applications of this dataset include:

• Pitch prediction
• Pitch ranking within a preset
• Predict a sound's preset

If you use this dataset in published researched, please cite Turian et al., "One Billion Audio Sounds from GPU-enabled Modular Synthesis", in Proceedings of the 23rd International Conference on Digital Audio Effects (DAFx2020), 2021:

@inproceedings{turian2021torchsynth,
title = {One Billion Audio Sounds from {GPU}-enabled Modular Synthesis},
author = {Joseph Turian and Jordie Shier and George Tzanetakis and Kirk McNally and Max Henry},
year = 2021,
month = Sep,
booktitle = {Proceedings of the 23rd International Conference on Digital Audio Effects (DAFx2020)},
location = {Vienna, Austria}
}