sentweet-twitter sentiment analysis using weka and java
TRANSCRIPT
![Page 1: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/1.jpg)
SentweetTWITTER SENTIMENT ANALYSIS TOOLBusiness intelligence course A.A. 2015/16
EGIDI SARA
![Page 2: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/2.jpg)
Motivation
Sentiment analysis Classification of the polarity of a given text in a
document, sentence or phrase Goal: determine whether the expressed opinion is
positive or negative Twitter
Microblogging tool, small sentences are less ambiguous
Variable audience Stock Market Products opinion Political elections
![Page 3: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/3.jpg)
Twitter corpus (2)
Preprocessing
Tokenizer
Feature Extraction
Classify
User input
Retrieve tweets
Preprocess
Classify
Roadmap
![Page 4: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/4.jpg)
The corpus
Two datasets: STS Stanford twitter corpus
Hand-labelled, different subjects40000 labelled balanced tweetsTweets from 2010
Auto generated using smiles ad labelsTwitter request rate limits
![Page 5: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/5.jpg)
Preprocessing
Remove RTs English tweets Remove URLs, mentions, numbers Replace repeated characters
Replace emoticons by their polarity (auto generated database)
Have you heard about TEDx speech ? So great!by @yulia Soooin #Milan
https://www.ted.com/talks/insightful_human_portraits_made_from_data
![Page 6: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/6.jpg)
Filters
Feature extractor Weka’s StringToWordVector
Stemmer Stoplist IDF-FT Tokenizer
Attribute Selection InfoGain and Ranker
![Page 7: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/7.jpg)
Classifiers
FilteredClassifier (uses filters just on training set) SupportVectorMachine Naïve Bayes Naïve Bayes Multinomial J48 Decision tree
Naïve Bayes Multinomial Text ( only Weka 3.8 ) No attribute selection needed
![Page 8: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/8.jpg)
Results
![Page 9: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/9.jpg)
Implementation• Twitter4J• TwitterAPI• JavaFX
![Page 10: Sentweet-Twitter sentiment analysis using WEKA and Java](https://reader035.vdocuments.us/reader035/viewer/2022062901/58f0add61a28ab56618b45cd/html5/thumbnails/10.jpg)
Thanks for your attention