Researchers at Carnegie Mellon University in Pittsburgh and Cornell University in Ithaca have developed a new algorithm that can sort out news of important events from entirely trivial details in Twitter streams.
The algorithm developed by researchers Jiwei Li and Claire Cardie can depict important events of an individuals life without knowing anything about them. The team of researchers tested the algorithm on 20 ordinary twitter users and 20 celebrities over a 21 month period from 2011 to 2013.
According to ‘MIT Technology Review’, the researchers asked 20 ordinary users to enter their most important tweets manually, to depict their own life history. For the celebrities, Li and Cardie used Wikipedia biographies to create ‘gold standard’ life histories manually.
Then they compared the life histories generated against the ones generated by their algorithm. The results were quiet accurate and the algorithm could pick out many life events accurately. “Experiments on real Twitter data quantitatively demonstrate the effectiveness of our method,” they say.
However this works for users who have twitter accounts and update their status regularly. The user also need to have enough followers to allow the algorithm to spot the unique pattern of responses that identifies important tweets.
“It can be extended to any individual, (eg friend, competitor or movie star), if only he or she has a twitter account,” they added.
A recent study by Researchers from Media Effects Research Laboratory found that users profiles on social media sites like Facebook, can hint at an individuals self-esteem and self-determination. The study depicted that people with lower as well as high self esteem spend a lot of time on building their social media profiles. The survey found that people with lower self esteem constantly monitor posts and updates about themselves, and people with high self esteem add more information about themselves on social networking sites.
Source: MIIT Technology Review