jessvb

Convo: What does conversational programming need?

This Gist contains additional information about the study presented in "Convo: What does conversational programming need?" at VL/HCC 2020.

The study can be cited as follows:

Van Brummelen, J., Weng, K., Lin, P., & Yeo, C. (2020). Convo: What does conversational programming need?. In 2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC).

or with BibTeX:

jessvb

How to use this file to process your Zoom transcription

1. Copy process_zoom_transcript.js to your computer.
2. Copy (e.g., from the Zoom web browser auto-scroll feature) your transcript into a text file called transcript.txt (case sensitive) in the same location where process_zoom_transcript.js is saved. (Note: DON'T use the official .vtt file.)
3. Edit process_zoom_transcript.js to contain names and name-replacements in the namesAndReplacements variable. For example, if "Ada Lovelace" is in your transcript, update the variable like so:

const namesAndReplacements = [{
        name: 'Ada Lovelace',
        replacement: 'Whatever Codename You Want'
    },
 {

jessvb

Teaching Tech to Talk: K-12 Conversational Artificial Intelligence Literacy Curriculum and Development Tools

This Gist contains additional information about the studies presented in "Teaching Tech to Talk: K-12 Conversational Artificial Intelligence Literacy Curriculum and Development Tools" at EAAI 2021 (focused on learning outcomes) and "'Alexa, Can I Program You?': Student Perceptions of Conversational Artificial Intelligence Before and After Programming Alexa" at IDC 2021 (focused on student perceptions of Alexa). There is also a video demo of the work.

Contents:

• Appendix A contains code snippets from the "cookbook" conversational AI skill developed in MIT App Inventor.
• [Appendix B](https://gist.github.com/jessvb/1cd959e32415a6ad4389761c49b54bbf#appendix-b-workshop-curriculum---activities-and-p

jessvb

Engaging Teachers to Co-Design Integrated AI Curriculum for K-12 Classrooms

This Gist contains the curricula from the co-design study presented in the paper, "Engaging Teachers to Co-Design Integrated AI Curriculum for K-12 Classrooms", at CHI '21. An overview of the study can be found in this video:

You can find the AI-integrated lesson plans (as described in the paper) below:

• Appendix A contains the "exemplar" integrated AI curriculum, which was based on one of the teacher's ideas for an AI-physics activity.
• [Appendix B](https://gist.github.com/jessvb/f415307d4696e6754e2f2e39a0

jessvb

How to approach statistics

Before you code, do three things:

1. Think about what you want to show in your data. For example, how would you like to ultimately visualize it or what would you ultimately like to say about it? Here are some helpful info graphics from a data science cheatsheet article on Medium:

2. Do quick initial visualizations of your data to get a sense of their distributions, whether it's actually worth doing a statistical test (i.e., does it look like there might be a significant difference?), and whether there are any outliers (which could be interesting in themselves! E.g., why did that particular participant choose xyz vs. how the

jessvb

## This is a demo of text generation with GPT-2 (Generative pretrained transformer)
## Copy this file to a working directory to which you have write acess  and
## run it with python3 using the shell command
## python3 gpt2_no_finetuning.py

## WARNING: This program can generate uncannily realistic output.  But the output
## can also be biased, controversial, and obscene.  If you distribute the program or
## the reults to others, include appropriate disclaimers.

import os

jessvb

Notes

To create a JSON of your data that can be used in vega-lite, you can use python pandas to_json function with the 'records' orientation:

import pandas as pd

inputFile = "/path/to/csvs/inputfile.csv"
outputFile = "/path/to/output/ourputfile.json"

df = pd.DataFrame()
df = pd.read_csv(inputFile)

jessvb

Learning Affects Trust: Design Recommendations and Concepts for Teaching Children—and Nearly Anyone—about Conversational Agents

This Gist contains the appendix from the study presented in the paper, "Learning Affects Trust: Design Recommendations and Concepts for Teaching Children—and Nearly Anyone—about Conversational Agents" (EAAI at AAAI 2023). You can find a preprint of this article on arXiv.

The study can be cited as follows:

Van Brummelen, J., Tian, M. C., Kelleher, M., Nguyen, N. H. (2023). Learning Affects Trust: Design Recommendations and Concepts for Teaching Children—and Nearly Anyone—about Conversational Agents. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37).

or with BibTeX:

jessvb

What Do Children and Parents Want and Perceive in Conversational Agents? Towards Transparent, Trustworthy, Democratized Agents

This Gist contains the appendix from the study presented in the paper, "What Do Children and Parents Want and Perceive in Conversational Agents? Towards Transparent, Trustworthy, Democratized Agents" (IDC 2023). You can find a preprint of this article on arXiv.

The study can be cited as follows:

Van Brummelen, J., Kelleher, M., Tian, M. C., Nguyen, N. H. (2022). What Do Children and Parents Want and Perceive in Conversational Agents? Towards Transparent, Trustworthy, Democratized Agents. In Proceedings of the 22nd ACM Conference on Interaction Design and Children (IDC'23).

or with BibTeX: