🏡We have analysed over 1 million forum interactions to identify what homeowners say about home heating and heat pumps when posting in online forums. 🏡 Read our report and explore our dashboard here: https://t.co/GkrXHPOi7T More in thread ⬇️

🏡 We've analysed over 1 million forum interactions relating to home heating posted in the past 20 years. 🍃Read our learnings here: https://t.co/Z9NtkJXWYr 🖥️ Access our GitHub repository: https://t.co/pwb4II9UYo 🧑‍💻 Check our technical appendix:

✨ Are you a data scientist? Do you want to learn about analysing online forums text data? You've heard about topic modelling but unsure where to start? Do you need a resource on sentiment analysis?

@aidan_s_kelly Many people at @nesta_uk provided support during this project: @CathSleeman , @lizgzil , @KandersKarlis , @_JackVines , Daniel Lewis, @ACJSissons , @AdrianStymne , @CodrinaCretu , @andymarsden_, Oliver Zanetti, @gebarnett1002 , Zayn Meghji, Elin Price and Robert Harris.

🙌Acknowledgements:🙌 - @aidan_s_kelly for delivering the data science work with me!

🤓The methodologies we used and the code we shared publicly can be applied to other domain areas/ other sources of forum/text data.

🔍Main takeaways: - There has been an increased interest in heat pumps over time! - Homeowners are still facing issues that are preventing them from getting a heat pump. @nesta_uk's sustainable future team has been working across most of them!

You can also see more information for some of the above topics. Cost can be split into several sub-themes including the upfront cost of installing a heat pump, the running costs of having a heat pump as a heating system and the related rise of electricity prices.

Here we have the same for the second forum, which is more focused on self-building.

The topics of conversation identified in the context of heat pump conversations and respective breakdown of sentiment, for one of the forums analysed - where we find mostly opinions from homeowners. NB: those who are unhappy are more likely to share their negative experiences.

🆕 Some of the learnings: 🆕 For most of the 2000s and 2010s, heat pumps were a niche topic on the forums we analysed. But interest has surged, and they were the 7th most discussed energy / heat topic in 2023.

To know more, you can: - read our technical appendix: https://t.co/zJkVOfJuw0 - check our code through this GitHub repository:

📈 About the data science: 📈 We have identified topics of conversation using a topic modelling approach called BERTopic. We used sentiment analysis to identify the share of interactions that were positive, neutral or negative.

Excited to have kicked off @nesta_uk's new project on creating energy use profiles from smart meter data. Lots of hard work lined up from @SofiaBrasPinto and colleagues in the coming months. Watch this space to see how it progresses. https://t.co/6TcgSn6mih

My amazing bff is now a Doctor! I’m so proud ❤️

I wrote a tutorial on how to use YData-Profiling (by @YData_ai) and @expectgreatdata - two Python packages that will speed up your exploratory data analysis and data quality assessments! Go check it out 🤓 https://t.co/kXD64dTXHE

New year, new default data manipulation package? I’ve written about some small changes I’ve made to speed up my normal data workflow with @DataPolars and @ApacheParquet

I've decided to do an unofficial @nesta_uk #HeatPumpAdventCalendar . . . just to prove how much we really love low carbon heating. So here, for Day 1, is our lovely Sustainable Future team at the Mitsubishi Electric factory in Glasgow (guided by the wonderful @kyle_usher):

Do you want to collect Twitter data, but don’t know where to start? Are you a Python enthusiast? Search no more🤓 Check out this medium post I wrote with all you need to get started with Twitter API v2 using Python. https://t.co/46fJv1MclU