Random Records

 - Again, I am testing whether the model is smart enough to generate the summary and podcast from my slide. - Though, I can detect a few mistakes but if we prepare the slide well enough, the model can generate a very useful podcast. - No wonder - if we are so addictive to the tool - it's kinda kill the creativity. - NotebookLM cannot do the task with mute video; it cannot guest what this video is about. I have never tried to put more info (text-based) for the mute video in order to train the model. - It is pretty neat! - Original slide:  Lab_ergonomics_slide Below is the podcast generated  from the lab ergonomics slide. Enjoy :) Text part Summary This slide deck presents information on lab ergonomics within a medical research laboratory setting, as indicated by the title slide and subsequent content. It covers regulations and guidelines relevant to this environment, touching upon aspects like chemical safety (mentioned in the context of principal investigator roles and la...

Note: Public discourse and sentiment during the COVID 19 pandemic: Using Latent Dirichlet Allocation for topic modeling on Twitter doi: 10.1371/journal.pone.0239441 Aim:  Twitter uses’ discourse + physiological reactions to COVID19 (output based on word) Method Using machine learning to analyse 1.9 million Tweets (written in English) - related to Coronavirus Collection 23 Jan 2020 - 7 Mar 2020 11 salient topics แยกออกมาเป็น 10 กลุ่ม “updates about confirmed cases,”  “COVID-19 related death,”  “cases outside China (worldwide),”  “COVID-19 outbreak in South Korea,”  “early signs of the outbreak in New York,”  “Diamond Princess cruise,”  “economic impact,” “Preventive measures,” “Authorities,” “supply chain Results Not reveal treatments and symptoms related messages Sentiment analysis fear for nature of coronavirus implications and limitation -- discussed in maintext Machine learning approach; (no code deposit) Latent topics relates to COVID19 identified ...