In the News: Project Starline, NLP Annotations, and Earth Day Special
This week, we cover the future of remote communication in Google Starline. Next, we discuss the contributions of NLP annotations for language analysis. We close out the newsletter on a positive note by explaining how AI can help protect ecosystems.
Project Starline Improves Remote Communication
By: Annika Lin
Google’s Project Starline released findings this past week showing that it outperforms traditional video conferencing in terms of conversation dynamics, video meeting fatigue, and attentiveness. Project Starline renders people at a natural scale on a 3D display and enables natural eye contact. Its study participants expressed that Project Starline was a significant improvement over traditional video conferencing in highly controlled lab experiments, as well as when they used Project Starline for their actual work meetings.
To measure video meeting fatigue, Google used the Zoom Exhaustion and Fatigue (ZEF) Scale and also measured participants’ reaction times on a complex cognitive task originally used in cognitive psychology. Assuming that more fatigue would slow down reaction times, they repurposed this task as a proxy for video meeting fatigue. They found that participants reported significantly less video meeting fatigue on the ZEF Scale (-31%) and had faster reaction times (-12%) on the cognitive task after using Project Starline compared to traditional video conferencing. Overall, Google found strong evidence that Project Starline delivered across their four main metrics, with over 87% of participants expressing that their meetings in Project Starline were better than their previous experiences with traditional video conferencing.
Want to learn more about Project Starline and the future of remote communication? Click on the link above!
What are NLP Annotations?
By: Spencer Karp
Natural language processing (NLP) has enabled us to analyze text, something believed to be impossible to analyze automatically not too long ago. NLP annotations have made this process easier. NLP annotations are labels that an algorithm can place on a certain word or phrase that relates to a specific goal. For example, it can label a part of speech or identify names, dates, and other specialized terms. It can also label the sentiment of a word or phrase. This information can be especially useful when reading long bodies of work and can expedite the analysis of any text. For sentiment analysis, it can be used to quickly label positive and negative reviews, and used in conjunction with more NLP annotating could even give insight into certain products, or people that are garnering the highest and lowest ratings.
In addition to helping people analyze text and speech recordings, the annotation process can be extrapolated to images and video. The same annotation process can be used to label sections of images that may be of interest, and can also label segments of video as a certain activity such as a person walking. NLP annotations allow for far more advanced language analysis and will surely be used as we progress towards a world full of chatbots. If you’re interested in an example, check out this one!
How AI is making the future greener
By: Sam Wirth
In a recent study published in the journal Nature Conservation, Dr. Neda Bihamta Toosi and her team investigated the potential of using machine learning to classify mangrove ecosystems, which are under threat due to degradation and disappearing. The researchers developed a novel method with a focus on landscape ecology for mapping the spatial disturbance of mangrove ecosystems, utilizing object-oriented classification of fused Sentinel images, and model-based landscape metrics and principal component analysis techniques. The study’s findings revealed that this approach significantly improved the accuracy of mangrove land use/land cover classification. By utilizing this innovative approach, the research team believes that they can supply information on land cover change trends that influence the development and management of mangrove ecosystems, promoting improved planning and decision-making to support the sustainable conservation of these coastal areas. This groundbreaking work presents a promising avenue for safeguarding these vital ecosystems and ensuring their preservation for generations to come.
