Difference between revisions of "Analyzing URL Chatter on Twitter"
From Knoesis wiki
| Line 1: | Line 1: | ||
==Project Description== | ==Project Description== | ||
===Objectives=== | ===Objectives=== | ||
| − | Classify the content of the urls | + | |
| − | Understand user perception of the websites | + | * Classify the content of the urls |
| + | * Understand user perception of the websites | ||
===Motivation=== | ===Motivation=== | ||
| Line 9: | Line 10: | ||
==Status== | ==Status== | ||
| + | ===Week 1=== | ||
| + | * Extracting the Urls from the tweets. | ||
| + | * Recognizing the short/tiny Urls and transforming it into the long Urls. | ||
| + | |||
| + | ===Week 2=== | ||
| + | * Creating a table for the Urls and the tweets to store the urls | ||
| + | |||
Revision as of 22:48, 6 November 2009
Contents
[hide]Project Description
Objectives
- Classify the content of the urls
- Understand user perception of the websites
Motivation
- Search Engine Perspective - How to choose a page which is interesting to the user, given the keywords
- Publisher Perspective - What do people think about the page(URL)
Status
Week 1
- Extracting the Urls from the tweets.
- Recognizing the short/tiny Urls and transforming it into the long Urls.
Week 2
- Creating a table for the Urls and the tweets to store the urls
Future work
1. Make sure the Url is not short by checking it recursively 2. Themes-Entity extraction from the tweets rather than using the present available themes
