User Classification For Informal Online Politcal Discourse
From Google TechTalks · 1:03:43
Show by Google TechTalks
Google Tech TalkJanuary 16, 2007ABSTRACTWeblogs, message boards, chat rooms logs, and other informal web texts are an incredibly rich knowledge base. However, the nature of these texts often makes them unsuitable for analysis using many standard natural language processing methods. This talk will describe on-going work in classification of participants in informal on-line political discourse. Lexically-oriented methods, such as sentiment analysis and text classification, have worked well in other domains but perform poorly on this task. We have achieved better results by augmenting these methods with social network analysis, exploiting information about the structure of the on-line community...Uploaded 08-10-07
More episodes of Google TechTalks
More episodes
- Making Great Decisions
- Streaming Private Continual Counting via Binning
- Distributed Testing with SmartFrog
- Differentially Private Synthetic Data without Training
- A Dynamic Network Layer for Advanced Cloud Computing
- Data Representation/Laplace Operator
- Persistent Pre-Training Poisoning of LLMs
- Threat Models for Memorization: Privacy, Copyright, and Everything In-Between
- Technology Assisted Reading Acquisition: Children Acquiring Literacy Naturally
- sex on the internet, the realities of porn, sexual privacy,
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.