Tweeting for Hillary - DS 501 case study 1
Download as PPTX, PDF1 like164 views
The document discusses a case study on collecting and analyzing Twitter data related to Hillary Clinton's campaign, highlighting the importance of data-driven decision making in political campaigns. It details the collection of approximately 15.5k tweets, sentiment analysis, and popular hashtags which can provide insights into public perception of the candidate. The study concludes that while useful, the sample size may not be sufficient for comprehensive analysis, suggesting further exploration of Twitter's potential for campaign strategies.
Tweeting for Hillary - DS 501 case study 1
- 1. Tweeting for Hillary Li Meng, Matt Beaulieu, ML Tlachac, Yousef Fadila DS 501 : Introduction To Data Science – Case Study 1: Collecting Data from Twitter https://github.com/yousef-fadila/casestudy1/blob/master/CaseStudy1.ipynb
- 2. “The more compelling campaign is a direct result of better data collection, analysis and smart decision making” -PromptCloud
- 3. Motivation Social media is a means for getting political news, and initiating political discussion Being able to interpret data with regards to the election would give a campaign manager live feedback on how their candidates actions likely impact polling This allows them to gain an advantage by reacting accordingly to changing political climates
- 4. The Data Pulled about 15.5K Tweets from the twitter streaming API Filter based on: Language: en Tweets mentioning @Hillary Clinton Can then process hashtags, mentions, and relevant words, to
- 5. Most Frequent Words Appearances Word 1240 trump 915 hillary 113 benghazi 346 cant 142 didnt 252 doesnt 146 poorest 117 trumps 130 wont 259 pneumonia 87 footing 192 liar 232 donors 541 dont 45 dnc Appearances Word 245 thats 91 isnt 41 tweet 63 ive 85 nypd 142 systematically 66 whats 68 cough 61 hypocrisy 32 dishonesty 103 crooked 40 theres 47 stamina 66 unfit 30 scum
- 6. Types of Frequent Words 1. Opponent: trump, trumps 2. Criticism: unfit, liar, hypocrisy 3. Topics: bodyguards, benghazi, poorest, blackmail, pneumonia, audiobooks 4. Patterns: cant, doesnt, didnt, wont, dont, isnt
- 8. Entity Popularity Screen Name Mentions HillaryClinton 15421 RealDonaldTrump 2718 FoxNews 1532 POTUS 503 CNN 481 politico 283 timkaine 263 FLOTUS 245 MSNBC 244 USAneedsTRUMP 235 Popular Mentions with @HillaryClinton Popular #hashtags with @HillaryClinton Hashtag Count #MAGA 385 #ImWithHer 351 #SpecialReport 209 #NeverHillary 178 #DNCLeak 177 #HispanicHeritageMonth 163 #tcot 156 #Trump 149 #TrumpPence16 125 #HillaryHealth 102
- 10. Hillary’s Friends ID Screen Name 571202103 Medium 21337440 ChildDefender 23449384 amberdiscko 128790234 Samynemir 1656913327 sarajacobs89 325886383 SammyKoppelman 802430450 Natasha_S_Law 729761993461248000 ktvibbs 115740215 SarahAudelo 34782406 Lincoln_Ross 3044781131 HillaryforAR 113298560 GunaRockYa 15972271 CdotDukes 582037089 MiguelAyala312 734768872625188864 AndrewBatesNC 41021335 TroyClair 4736170399 BrianZuzenak 150885854 SarahPeckVA 231673 yianni 125083946 GillDrummond ● Communication Directors ● Charities ● Media Websites ● United States Senators ● etc.
- 11. Sentiment Analysis Using Python’s NLTK text classifier, classified each tweet as “Positive”, “Negative”, or “Neutral”. Could give an idea of how “twitter” felt about Hillary Clinton Positive Neutral Negative
- 12. Geographic Analysis Using the “positivity” of each tweet, we formed a ratio of positive and negative tweets, and compared it national polling data, to see how tweet hashtags related to polling data, if at all.
- 13. Sentiment Analysis on Text Hashtags in Positive Tweets Count #HispanicHeritageMonth 118 #ImWithHer 107 #MAGA 72 #tcot 65 #Democrats 50 #RedNationRising 46 #WakeUpAmerica 43 #NeverHillary 32 #HillaryClinton 31 Hashtags in Negative Tweets Count #ImWithHer 74 #LatinosWithTrump 51 #AmericansUnitedForTrump 49 #MAGA 42 #NeverHillary 39 #CrookedHillary 38 ● Broke down the most popular hashtags in positive and negative tweets ● Some hashtags, in either table, seemed out of place ● This could be part of the source of error in the sentiment classification
- 14. Sentiment analysis on Hashtags Manually identify positive and negative hashtags, and use this to determine popular words in tweets containing those hashtags in order to re-train the NLTK alogrithim Positive Hashtags include... ● Never Trump ● Hillary2016 ● StrongerTogether ● Vote ● UnitedBlue Negative Hashtags include... ● MAGA ● NeverHillary ● CrookedHillary ● LatinoswithTrump ● AmericansUnitedwithTrump
- 16. Conclusions Word frequency analysis revealed relevant tweets to Clinton, and issues that she could consider addressing, or at least know what’s being talked about. Judging tweets by positive or negative sentiment gave mixed results. Training the positive and negative classifier on positive or negative hashtags proved more insightful. Ultimately, 15.5K tweets is not enough data, especially when separating it by state. Twitter has great potential to be useful to campaigns.
- 17. Thank You Questions? Source code and Charts: https://github.com/yousef-fadila/casestudy1/blob/master/CaseStudy1.ipynb