You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I was looking through a bunch of tweets from a log file with many saying stuff like: "good morning", "i'm not awake yet", "I just wan't some dunkin' donuts". It should be possible to estimate the local time of day from the content of the tweet.
This might be useful for estimating the time of day for documents that are not tweets, such as blogs, letters, or other documents. We could try to classify the entire document at once, or try to estimate the time of day for each sentence, and then try to figure out a time for the entire document.
Idea was originally recorded 3/16/13 at 11:26.
The text was updated successfully, but these errors were encountered:
I was looking through a bunch of tweets from a log file with many saying stuff like: "good morning", "i'm not awake yet", "I just wan't some dunkin' donuts". It should be possible to estimate the local time of day from the content of the tweet.
This might be useful for estimating the time of day for documents that are not tweets, such as blogs, letters, or other documents. We could try to classify the entire document at once, or try to estimate the time of day for each sentence, and then try to figure out a time for the entire document.
Idea was originally recorded 3/16/13 at 11:26.
The text was updated successfully, but these errors were encountered: