Difference between revisions of "Cohen Courses:Tweet"
| Line 12: | Line 12: | ||
* tweet differently at different locations - e.g. a tweet made from a restaurant (about the food, the service, etc) maybe different from a tweet made from an office (about works, etc) | * tweet differently at different locations - e.g. a tweet made from a restaurant (about the food, the service, etc) maybe different from a tweet made from an office (about works, etc) | ||
* location is affected by time - e.g. a person is more likely to tweet from the office in the morning than from a nightspot | * location is affected by time - e.g. a person is more likely to tweet from the office in the morning than from a nightspot | ||
| − | * sentiment is affected by location - e.g. a person maybe more likely to feel sombre in the office than in travel spots | + | * sentiment is affected by location and time - e.g. a person maybe more likely to feel sombre in the office in weekdays than in travel spots in holidays or weekends |
| − | How locations of tweets change with time | + | How locations of tweets change with time represents geographical activity profile of the user. Such activity maybe structured across geographical space and across time. This structure is what we want to learn about the user based on his tweets. Using the structure and the tweet, we would like to infer the location from which the tweet is made. |
| − | The location categories to infer are taken from Foursquare categories: "Arts and Entertainment", "College and Education", "Food", "Home/Work/Other", "Nightlife Spots", "Great Outdoors", "Shops", "Travel Spots". | + | The location categories to infer are taken from Foursquare categories: "Arts and Entertainment", "College and Education", "Food", "Home/Work/Other", "Nightlife Spots", "Great Outdoors", "Shops", "Travel Spots". |
== Baseline & Dataset == | == Baseline & Dataset == | ||
Revision as of 00:04, 6 October 2011
Inferring geographical activity using Twitter.
Team Member(s)
Proposal
In this project we would like to infer the location category of a tweet based on the words in the tweet (including sentiments) and the time of the tweet. We believe Twitter users:
- tweet differently at different locations - e.g. a tweet made from a restaurant (about the food, the service, etc) maybe different from a tweet made from an office (about works, etc)
- location is affected by time - e.g. a person is more likely to tweet from the office in the morning than from a nightspot
- sentiment is affected by location and time - e.g. a person maybe more likely to feel sombre in the office in weekdays than in travel spots in holidays or weekends
How locations of tweets change with time represents geographical activity profile of the user. Such activity maybe structured across geographical space and across time. This structure is what we want to learn about the user based on his tweets. Using the structure and the tweet, we would like to infer the location from which the tweet is made.
The location categories to infer are taken from Foursquare categories: "Arts and Entertainment", "College and Education", "Food", "Home/Work/Other", "Nightlife Spots", "Great Outdoors", "Shops", "Travel Spots".
Baseline & Dataset
Related Work
- A Mixture Model of Demographic Lexical Variation by O'Connor et al., NIPS-2010 Workshop on Machine Learning and Social Computing
- A Latent Variable Model for Geographic Lexical Variation by Eisenstein et al., EMNLP 2010
- You Are Where You Tweet: A Content-Based Approach to Geo-locating Twitter Users by Cheng et al., CIKM 2010
- Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures by Golder and Macy, Science, Vol. 333 no. 6051 pp. 1878-1881, 30 September 2011
