Name
Abstract | ||
|---|---|---|
We investigate the predictive power behind the language of food on social media. We collect a corpus of over three million food-related posts from Twitter and demonstrate that many latent population characteristics can be directly predicted from this data: overweight rate, diabetes rate, political leaning, and home geographical location of authors. For all tasks, our language-based models significantly outperform the majority-class baselines. Performance is further improved with more complex natural language processing, such as topic modeling. We analyze which textual features have greatest predictive power for these datasets, providing insight into the connections between the language of food, geographic locale, and community characteristics. Lastly, we design and implement an online system for real-time query and visualization of the dataset. Visualization tools, such as geo-referenced heatmaps and temporal histograms, allow us to discover more complex, global patterns mirrored in the language of food. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/BigData.2014.7004305 | BigData Conference |
Keywords | DocType | Volume |
food products,natural language processing,social networking (online),Twitter,community characteristics,complex natural language processing,dataset visualization,diabetes rate,food-related posts,geo-referenced heatmaps,geographic locale,home geographical location,language-based models,language-of-food,latent population characteristics,majority-class baselines,overweight rate,political leaning,predictive power,real-time query,social media,temporal histograms,textual features,topic modeling,visualization tools | Journal | abs/1409.2195 |
ISSN | Citations | PageRank |
2639-1589 | 11 | 0.93 |
References | Authors | |
11 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Fried | 1 | 83 | 7.69 |
| Mihai Surdeanu | 2 | 2582 | 174.69 |
| S. Kobourov | 3 | 11 | 0.93 |
| M. Hingle | 4 | 11 | 0.93 |