AIDR Tutorial (Artificial Intelligence for Disaster Response)
2 likes532 views
This document provides an overview of the AIDR (Artificial Intelligence for Disaster Response) system, including how it collects Twitter data through keywords, geographic regions, and following users. It also describes how AIDR allows users to classify collected data by defining classifiers and labels, and how the classifiers are generated based on human-tagged tweets.
AIDR Tutorial (Artificial Intelligence for Disaster Response)
- 2. Outline ≒ Data collec2on in AIDR ≒ Data classi鍖ca2on in AIDR ≒ Data view/download in AIDR
- 3. Data Collec2on in AIDR ≒ Twi:er data collec2on strategies that AIDR supports By keywords By geographical regions ≒ Strict: coordinates strictly inside geo boundaries ≒ Approximate: tweets from a place that overlaps with the geo boundaries. By following Twi:er users By keywords + regions ≒ Tweets that match any of the keywords and within the geo boundaries.
- 4. Data Collec2on Using Keywords ≒ Keywords limit = 400 ≒ One keyword could a single word like Su鍖olk or a phrase Su鍖olk accident ≒ 1 keyword/phrase cannot be more than 60 bytes (1 char = 1 byte) ≒ Generic keywords collect irrelevant tweets ≒ Speci鍖c keywords most likely collect relevant tweets
- 7. Following Twi:er Users For each user speci鍖ed, the tool will collect: ≒ Tweets created by the user. ≒ Tweets which are retweeted by the user. ≒ Replies to any Tweet created by the user. ≒ Retweets of any Tweet created by the user. ≒ Manual replies, created without pressing a reply bu:on (e.g. @twi:erapi I agree). The tool will not contain: ≒ Tweets men2oning the user (e.g. Hello @twi:erapi!). ≒ Manual Retweets created without pressing a Retweet bu:on (e.g. RT @twi:erapi The API is great). ≒ Tweets by protected users. Use comma-separated list of TwiFer user id (hFp://geFwiFerid.com/)
- 9. Classi鍖er UI
- 12. Classi鍖er Genera2on ≒ Check the classi鍖er status (UI) First classi鍖er/model will be up ager 50 labeled tweets, ideally equally distributed among labels If no model appears ager 50 tags, keep tagging ≒ Human-tagged items (the more the be:er) ≒ 40 more needed to re-train (next classi鍖er target) ≒ Machine-tagged items (keep an eye on misclassi鍖ca2ons) ≒ Quality (ideally should be 90 < AUC != 100)