Data mining on twitter - ADE2016
* hybrid classifier implementation
* visualize sentiment(recognize differences between categories)
* research on how to categorize tweets using both text and features
* SVM optimization(feature selection,preprocessing techniques)
* feature based classification(SVM)
* Nayve bayes optimization
* sentiment analysis(VADER)
* Naive Bayes algorithm
* Map/reduce procedure for twitter's feature
* Text base classification SGD
* Visualize dataset's feature
* Starting a map/reduce procedure in order to calculate the values of twitter's feature
* Word count map/reduce procedure
* Manually categorize topics
* Manually categorize topics on categories
* Working on classification algorithms
* Collecting tweets
* Manually categorize topics on categories
* Collecting tweets
* program to analyze and visualize dataset's feature
* Database creation
* Collecting tweets
* progress report
* --(final exam's period)
* collecting twitter Data
* solution determination
* solution plan(steps)
* research on classification algorithms
* research on papers relate to topic classification
* research on papers relate to tweet classification
* presentation(26/10)
* research on how twitter works(features)
* impove map-reduce procedures
* Grouping London's tweets :
* by districts ** using a map-reduce procedure
* by map locations ** using a map-reduce procedure