Cristia, Bergelson, Casillas
hardware in mee.dev and beyond; audio, video, and additional modalities; hardware-dependent clothing choices; logistics in view of equipment
carrying out a 12+ hour sample recording using oneself as participant
- Hands-on practice recording
- Adaptation to individuals
- Ethics & law only in preparation for the task
Meet up with lecturers (Cristia, Bergelson, Casillas)
topics:
- Evaluating your own hardware needs
- Creating materials to inform families
- Simulated logistics management
Cychosz, Soderstrom
Overview of legal & ethical issues specific to or exacerbated by LFRs, including informed consent, personal data protection, automated processing
Automatically analyze your self-recorded audio. Learn about the legislation that applies to the country/region where you'll be collecting your data from, and reflect about the special ethical considerations that may apply to you. Listen to samples of the recording you took yesterday, then share the samples (or a selection of them) with a peer. Compare and contrast legislation, ethical concerns, and anything else that might have come up as you listened to your own audio data.
Meet up with lecturers (Cychosz, Soderstrom), topics:
- Legal & ethical issues arising in your own project
- Organizing and storing data: best feasible practices for you
- Feedback on your own DMP
- Run validation methods on your annotations against a gold standard
- Extract evaluation/correlation metrics between annotations (precision, recall, f-score, correlation metrics)
- Interpret implications of those metrics on the data, explore other/complementary evaluation methods.
Meet up with lecturers (Cristia, Cychosz, Soderstrom), topics:
- Sampling, annotation scheme, & software for your own research goals
- Feedback on annotator instructions
- Setting up and running analyses using VTC and ALICE in your own computer
- Interpreting the results: how to read the metrics and outputs
- Identifying errors and adjustments in automated analyses