A5051680500- Natural Language Processing Techniques
- Web Data Mining and Analysis
- Computational and Text Analysis Methods
- Geophysics and Gravity Measurements
- Climate variability and models
- Microplastics and Plastic Pollution
- Recycling and Waste Management Techniques
- Topic Modeling
- Atmospheric and Environmental Gas Dynamics
- Sentiment Analysis and Opinion Mining
- Data Visualization and Analytics
- Ethics and Social Impacts of AI
- Municipal Solid Waste Management
University of California, Berkeley
2023-2024
Plastic production and plastic pollution have a negative effect on our environment, environmental justice, climate change. Using detailed global regional plastics datasets coupled with socioeconomic data, we employ machine learning to predict that, without intervention, annual mismanaged waste will nearly double 121 million metric tonnes (Mt) [100 139 Mt 95% confidence interval] by 2050. Annual greenhouse gas emissions from the system are projected grow 37% 3.35 billion CO 2 equivalent (3.09...
This multi-disciplinary case study details how a public web application combines information and game design to visualize effects of user-defined policies intended reduce plastic waste. Contextualizing this open source software within broader lineage digital media research, user experience exploration outlines potential directions for facilitating conversation between artificial intelligence, scientists, decision makers during an iterative policy building process. Furthermore, system...
Proposing and comparing multiple neural network-based techniques in order to choose an optimized configuration, the described method can train a classifier predict publisher of news articles given short snippet text. This classifier's scores then help creation exemplar-based search engine. Specifically, this model be used compare linguistic patterns between different organizations identify prototypical for source that most "exemplify" publisher’s coverage. Finally, these "exemplars" are made...
Program produces longitudinal catch data which support ocean health
An article's tone and framing not only influence an audience's perception of a story but may also reveal attributes author identity bias. Building upon prior media, psychological, machine learning research, this neural network-based system detects those writing characteristics in ten news agencies' reporting, discovering patterns that, intentional or not, agency's topical perspectives common contextualization patterns. Specifically, linguistic markers different organizations through newly...
Proposing and comparing multiple neural network-based techniques in order to choose an optimized configuration, the described method can train a classifier predict publisher of news articles given short snippet text. Furthermore, this model be used compare linguistic patterns between different organizations identify prototypical for source that most "exemplify" publisher’s coverage. Finally, these "exemplars" are made searchable through open browser-based application.
Proposing and comparing multiple neural network-based techniques in order to choose an optimized configuration, the described method can train a classifier predict publisher of news articles given short snippet text. This classifier's scores then help creation exemplar-based search engine. Specifically, this model be used compare linguistic patterns between different organizations identify prototypical for source that most "exemplify" publisher’s coverage. Finally, these "exemplars" are made...
Proposing and comparing multiple neural network-based techniques in order to choose an optimized configuration, the described method can train a classifier predict publisher of news articles given short snippet text. This classifier's scores then help creation exemplar-based search engine. Specifically, this model be used compare linguistic patterns between different organizations identify prototypical for source that most "exemplify" publisher’s coverage. Finally, these "exemplars" are made...