Model Matters

Model Matters Getting the best results when exploring AI Artificial Intelligence is a revolutionary breakthrough. It can help researchers understand qualitative data in new, interesting, powerful ways. Occasionally, as I develop and refine new features for Transana, I...

Understanding AI – A question of accuracy

AI results based on Large Language Modelsare probabilistic, not deterministic. If you want to use AI to explore your qualitative data, it's very important to understand exactly what this means.Introduction Large Language Models are not intelligent in any recognizable...

What can AI do? What can’t it do?

I received the following question as part of a recent support inquiry:Do we need to manually create collections and keywords ourselves, or can they be suggested via an embedded AI tool?Here is my reply:Yes, you need to create Collections and Keywords yourself. And...

From Summaries to Time-Coded Transcripts: Unlocking Interactive Analysis

Introduction When we ask ChatGPT to summarize a transcript, we get a useful overview of the content — a snapshot of key ideas, but without attention to how those ideas unfold over time. In qualitative data analysis, especially when working with video, time matters....

Prompting Analysis: Comparing AI and Human Thematic Coding in Transana

Introduction When you work with transcripts, interviews, or debates, the amount of text can feel overwhelming. Thematic analysis is the tool that helps researchers make sense of it all. It finds patterns in what people are saying so we can see the big picture. It...

Faster Whisper in Transana 5.30: Accuracy and Processing Speed (3 of 3)

Introduction In the two previous blog posts, we looked at the accuracy of transcripts of four English language media files using the eleven available Faster Whisper transcription models. Two of the four media files featured excellent audio quality and two distinct...
Transcribing Overlapping Speech

Transcribing Overlapping Speech

My first thought as I watched the first U.S. Presidential debate of 2020 was "Oh, those poor transcribers."  I recognized the huge challenge this would present for transcribers, with constant interruptions and so much overlapping speech.  I knew it would strain a...

Transana and MacOS Catalina

Transana and MacOS Catalina

Apple recently released MacOS 10.15, known as Catalina, and made major changes to the way MacOS works "under the hood." While there was plenty of advanced notice about the changes, the scale of the changes needed means that many smaller software developers, including...

Importing Transcripts from Transcription Services

Importing Transcripts from Transcription Services

 We receive frequent inquiries about importing transcripts from automated online transcription services into Transana.  There are several issues to consider if you are thinking about having your media transcribed through a service, whether automated or manual.  Online...

Making Sense of Your Coded Data

Making Sense of Your Coded Data

So you’ve added a bunch of documents and images and episodes to Transana. You’ve developed a set of keywords that represent your coding system. You’ve made a bunch of selections and you’ve categorized and coded them. You’re ready to start working with Transana’s...

Categories

Archives