11 Years withWearables: Quantitative Analysis of Social Media, Academia, News Agencies, and Lead ...
summary
Quantitative analysis of 2009–2020 data from DBLP, PubMed, Twitter, Google News, Bing News, Kickstarter and Indiegogo uses 42 keywords and LDA topic modeling to label documents and a pre-trained BERT + 2-layer BiGRU pipeline to produce a 0–1 sentiment score per item; results show XR is the most-mentioned category, Exoskeleton sparks the strongest debate, and hyped wearables have a three-year hype lifetime; news and crowdfunding positivity do not strongly shift public sentiment, while fashion and healthcare wearables show the clearest market signals.
AI-written summary · about
related talks
45mKeynote: From Hypnotised to Heretic: Immunising Society Against Misinformation.
27mMining social media data of people with rare diseases
20mEmploying AI to extract actionable insights from qualitative user...
17mKnow Thyself: Introspective Personal Data Mining
45mDecoding Topics: A Comparative Analysis of Python’s Leading Topic Modeling Libraries Using Climate C
10mIntelligence in the Age of Plethora
35mFireside chat: Digital IQ and marketing big data
32mHow to be best in conveying the message by using NLP approach (Big Five modeling)