THE FLEETING IMPACT OF OUTRAGE AFP TORONTO 17

Size: px

Start display at page:

Download "THE FLEETING IMPACT OF OUTRAGE AFP TORONTO 17"

Theodora Gordon
6 years ago
Views:

1 THE FLEETING IMPACT OF OUTRAGE AFP TORONTO 17

4 Session Overview Welcome Introduction Opinion Mining Case Studies Q & A

5 What is Opinion Mining?

Opinion mining (also known as sentiment analysis) refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective

6 Opinion mining (also known as sentiment analysis) refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information Generally speaking, opinion data analysis aims to determine the attitude of a speaker or a writer with respect to some topic

7 CASE STUDY Brexit WHY ACCURATE OPINION DATA MATTERED

8 What the pundits said 48% Leave, 52% Remain Natalie Bennett, British Politician if you gave me 100 and offered me the chance to bet on it, I think I d say 52.5 for Remain EU referendum polls: Final ComRes poll shows significant lead for Remain 42% Leave, 58% Remain

9 What Social Media said 61% 59% 53% 57% 39% 41% 47% 43% LEAVE 56.9% REMAIN 43.1% 20 June 21 June 22 June 23 June Leave Remain

10 Research Methodology Tracked 500,000 online conversations in the week leading up to the vote. Identified the city in which the author was located through geo-location algorithms. Crowd-verified a sample of 10,000 mentions. Delivered daily sentiment analysis with a 95% confidence interval and a 2.5% margin of error.

Brexit prediction by regions Top cities by volume Top outlying regions London REMAIN Sheffield LEAVE Manchester REMAIN Newcastle upon Tyne LEAVE Edinburgh REMAIN Hull LEAVE Bristol

11 Brexit prediction by regions Top cities by volume Top outlying regions London REMAIN Sheffield LEAVE Manchester REMAIN Newcastle upon Tyne LEAVE Edinburgh REMAIN Hull LEAVE Bristol REMAIN Bournemouth LEAVE Glasgow REMAIN Coventry LEAVE Sheffield LEAVE Southampton LEAVE Cardiff REMAIN Leicester LEAVE Liverpool REMAIN Chester LEAVE Birmingham REMAIN Portsmouth LEAVE

12 CASE STUDY US Elections 2016 HOW SOCIAL MEDIA DATA TRUMPED THE POLLSTERS

What everybody else said What a Clinton landslide would look like http://fivethirtyeight.

tighten: Reuters/Ipsos http://www.reuters.

13 What everybody else said What a Clinton landslide would look like Clinton leads Trump by 5 points, swing states tighten: Reuters/Ipsos Clinton leads by 5 heading in to final weeks Trump won t win. In fact, the US could be on the brink of a liberal renaissance

14 Pro-Trump or anti-clinton unique authors as a percentage of all candidate sentiment 100% 75% 50% 25% 0% Oct 1 - Oct 23 Oct 24 - Oct 30 Oct 31 - Nov 6 Nov 7 Weighted average

Opinion Data accuracy outperforms polls BBC FIVETHIRTYEIGHT BRANDSEYE Colorado CLINTON CLINTON TRUMP Florida TRUMP CLINTON TRUMP Iowa TRUMP TRUMP TRUMP Michigan CLINTON CLINTON TRUMP Nevada TRUMP

15 Opinion Data accuracy outperforms polls BBC FIVETHIRTYEIGHT BRANDSEYE Colorado CLINTON CLINTON TRUMP Florida TRUMP CLINTON TRUMP Iowa TRUMP TRUMP TRUMP Michigan CLINTON CLINTON TRUMP Nevada TRUMP CLINTON CLINTON New Hampshire CLINTON CLINTON CLINTON North Carolina TRUMP CLINTON TRUMP Ohio TRUMP TRUMP TRUMP Pennsylvania CLINTON CLINTON TRUMP Virginia CLINTON CLINTON TRUMP Wisconsin CLINTON CLINTON TRUMP out of 11

16 Research Methodology Tracked 37 million mentions Geo-location algorithms identified the state in which the author was located. A random sample of over 200,000 mentions from key battleground states were sent to our crowd for verification. They delivered daily net sentiment towards Trump and Clinton with a 95% confidence interval and a 3.5% margin of error.

17 AI is not (yet) the answer SemEval-2017 Task 4 Sentiment Analysis in Twitter RANK AI SYSTEM ACCURACY 1 NNEMBs 66.4% 2 LIA 66.1% 3 BB_twtr 65.8% 4 Senti % 5 DataStories 65.1% Artificial Intelligence cannot understand the complexity and nuance of language in the world of social media. Semantic Evaluation 2017 Competition: Qatar Computing Research Institute, SemEval 2017, Task 4, Subtask A.

A mix of machine learning and crowd-sourced When machines are combined with the power of humans, accuracy can be achieved at 95%+ confidence levels verification to achieve unparalleled accuracy

18 A mix of machine learning and crowd-sourced When machines are combined with the power of humans, accuracy can be achieved at 95%+ confidence levels verification to achieve unparalleled accuracy through opinion data. For every term or topic tracked, a statistically significant sample of the mentions are processed through human crowds, to understand the nuance of conversation and to accurately identify both the topics driving conversation and the sentiment of the authors towards those topics. With accurate opinion data strategic and operational decision-makers in near real-time have an accurate gauge on what the public is thinking and feeling.

20 THE SYRIAN REFUGEE CRISIS: JAN 2015 SEP 2016

21 METHODOLOGY Mentions from 1 Jan Sep million mentions about the Syrian refugee crisis 23 k mentions human-verified by the BrandsEye crowd 0.7 margin of error with a 99% confidence level

22 CROWD VERIFIED DATA The crowd verified mentions from over 20 different languages Including English, Spanish, Turkish, French and Arabic The crowd also processed data from over 25 different countries

23 ARE PEOPLE PAYING ATTENTION?

OVERVIEW On a daily basis, an average of 95 156 people are talking about the Syrian refugee crisis.

730 6 561 5 353 6 092 5 571 5 136 5 203 5 632 6 114 6 372 7 363 8 026 8 551 9 737 9 848 10 316 11 444 11 513 11 240 11 445 12 380

24 OVERVIEW On a daily basis, an average of people are talking about the Syrian refugee crisis. An average of posts on social media about the Syrian refugee crisis daily AM 01 AM 02 AM 03 AM 04 AM 05 AM 06 AM 07 AM 08 AM 09 AM 10 AM 11 AM 12 PM 01 PM 02 PM 03 PM 04 PM 05 PM 06 PM 07 PM 08 PM 09 PM 10 PM 11 PM

25 COUNTRY BREAKDOWN Conversation from 245 countries, regions and islands across the world! UK: / day Germany: / day Canada: / day USA: / day Syria: / day Turkey: / day India: / day

1% Australia 21.5% Ukraine 13.9% South Africa 20.3% Ireland 13.

26 SENTIMENT BY COUNTRY Most Negative Most Positive Iceland 25.2% Lebanon 15.8% Unites States of America 24.7% Canada 14.1% Australia 21.5% Ukraine 13.9% South Africa 20.3% Ireland 13.5% Turkey 20.3% Germany 13.0% United Kingdom 20.1% United Kingdom 12.6% Brazil 20.1% Norway 12.4%

27 MOST ACTIVE AUDIENCES BY TWITTER BASE 0.45% Looking at amount of unique authors divided by total registered users on Twitter per country 0.40% 0.35% 0.30% 0.25% 0.20% 0.15% 0.10% 0.05% 0.00% Canada Malaysia Australia United Kingdom United States Italy Germany Nigeria Turkey South Africa

28 CONVERSATION WITHIN SYRIA

29 CONVERSATION ABOUT ALEPPO killed civilians people airstrikes injured regime #assad children russian #holocaustaleppo

30 People are talking! but are they contributing?

31 WHAT ABOUT DONATIONS? Looking at the comparison of mentions to donation, the story looks dismal 450, ,000 Alan Kurdi picture spreads global outrage 350, , , , , ,000 50, /1/2015 7/1/2015 8/1/2015 9/1/ /1/ /1/ /1/2015 People donating All people talking

32 DONATIONS THE CONVERSION RATE The death of Alan Kurdi caused a massive increase in people donating towards the Syrian Refugee cause. In the months leading up to this terrible tragedy, 1.2% of all people talking about it the Syrian Refugee crisis, made donations. In September, this increased to 11.5%. The months after, 2.9% of people talking about it, made donations. Overall, this is still only 2.7% of people donating to the cause. 450, , , , , , , ,000 50,000 0 Alan Kurdi picture spreads global outrage 6/1/2015 7/1/2015 8/1/2015 9/1/ /1/ /1/ /1/ *People donating plotted on secondary axis All people talking People donating

33 DONATIONS THE INSIGHT OF CORRELATION Correlation (definition): noun a mutual relationship or connection between two or more things. There is an R of 0.8 a strong correlation between the volume of conversation about Syrian Refugees and donations made. WHAT DOES THIS MEAN? The 450,000 more people are talking about it, the more donations! 400, , , , , , ,000 50, /1/2015 7/1/2015 8/1/2015 9/1/ /1/ /1/ /1/ All people talking People donating

34 How do we change this?

35 Campaigns analysis

36 E N G A G E M E N T * WHAT ARE THE MOST ENGAGING STORIES MOST ENGAGING POSTS Stories that mostly revolve around children and the human-centred story. The top 135 most engaging mentions received 12% of the total engagement around the Syrian refugee crisis. CAMPAIGN POSTS Campaigns accounted for 1% of the total engagement MIXTURE OF POSTS A mixture of news and human-interest stories and campaigns *DEFINED BY THE NUMBER OF SHARES OR COMMENTS POSTS RECIEVE

37 WHAT WERE THE MOST ENGAGING STORIES? 50% of the most engaged with stories referenced children 7 y/o Syrian girl tweeting about her experiences of living in Aleppo 71.1k Followers British news network 1.22M followers BBC reporter based in Beirut 10.7k followers

38 WHAT WERE THE MOST ENGAGING STORIES? The human story prevails

39 THE MOST ENGAGING CALL TO DONATE GIGI HADID American fashion model and TV personality retweets 3m people potentially saw this

5m people potentially saw this The post was the most engaged with campaign

40 HOW DID DONATE CAMPAIGNS FARE? This was only the 119 th most engaging post 7.5m people potentially saw this The post was the most engaged with campaign post football as a global sport appears to be key here Similarly this story generated 18k social mentions, with 141m people potentially seeing this

41 MOST ENGAGING AID AGENCY CONTENT

42 AID AGENCY CAMPAIGNS Content Analysis Aid agency posts tend to highlight certain instances of the situation in Syria or the refugee crisis. Most do not contain a call to action.

43 Other campaigns have been driven by multiple sources

Apple is the world s most profitable company, it pays over $7bn a year in

44 THE POWER OF A NAME We re often led to believe migration is a drain on the country s resources but Steve Jobs was the son of a Syrian migrant. Apple is the world s most profitable company, it pays over $7bn a year in taxes and it only exists because they allowed in a young man from Homs. - BANKSY

45 THE POWER OF STORY This story of a Syrian man selling pens in Lebanon, while carrying his sleeping daughter spurred ordinary citizens to act. Within 24 hours, $ had been raised from the crowdfunding platform IndieGogo.

46 How can we leverage public sentiment for change?

47 The stories of Alan Kurdi and Omran Daqneesh represented a pivotal turning point in how the world saw the Syrian refugee crisis

48 A(Y)LAN KURDI

49 BEFORE & AFTER - ALAN KURDI VOLUME OF CONVERSATION ON SOCIAL MEDIA 300,000 Paris attacks 250, ,000 Alan Kurdi s death shocks the world 150, ,000 50,000 3 months before Alan Kurdi mentions / week 1 month after mentions / week 1 month after mentions / week 0 Syrian Refugee conversation Alan Kurdi

50 ACTIVITY HALF-LIFE ALAN KURDI Moral Outrage has a much shorter half-life than general conversations 14,000 All Conversations Moral Outrage ,000 10,000 Charlie Hebdo cartoon ,000 3 Days 100 6, ,000 2, hrs

51 BEFORE & AFTER - ALAN KURDI SENTIMENT TOWARDS SYRIAN REFUGEES 70.0% Before Alan Kurdi: Negative: 26.1% Positive: 11.3% Change in sentiment: Negative: -7.9% Positive: +14.0% After Alan Kurdi: Negative: 18.2% Positive: 25.3% 60.0% 50.0% 40.0% 30.0% 20.0% 10.0% 0.0% Positive Negative

52 ALAN KURDI SENTIMENT INTENSITY Sentiment towards the death of Alan Kurdi Intense Outrage 5% Sympathetic 13% Mild Outrage 82%

53 OMRAN DAQNEESH

BEFORE & AFTER ANALYSIS OMRAN DAQNEESH 1,600,000 Bombing of aid trucks in Allepo 1,400,000 1,200,000 1,000,000 Omran Daqneesh s story goes viral 800,000 600,000 400,000 200,000 1 month before Omran

54 BEFORE & AFTER ANALYSIS OMRAN DAQNEESH 1,600,000 Bombing of aid trucks in Allepo 1,400,000 1,200,000 1,000,000 Omran Daqneesh s story goes viral 800, , , ,000 1 month before Omran Daqneesh 450 mentions / week 1 month after 46 k mentions / week 0 7/4/2016 7/11/2016 7/18/2016 7/25/2016 8/1/2016 8/8/2016 8/15/2016 8/22/2016 8/29/2016 9/5/2016 9/12/2016 9/19/2016 9/26/2016 Syrian Refugee conversation Omran Daqneesh

55 ACTIVITY HALF-LIFE OMRAN DAQNEESH As with the story of Alan Kurdi Moral Outrage has a short half-life 20,000 18,000 16,000 All Conversations Moral Outrage ,000 12,000 4 Days ,000 8, , hrs 200 4,000 2,

56 OMRAN DAQNEESH SENTIMENT INTENSITY Sentiment towards the assault on Omran Daqneesh Intense Outrage 1% Sympathetic 1% Mild Outrage 98%

57 PARIS ATTACKS

58 BEFORE & AFTER - ALAN KURDI VOLUME OF CONVERSATION ON SOCIAL MEDIA Paris attacks 300, , ,000 Alan Kurdi s death shocks the world 150,000 1 month after 100,000 50,000 3 months before Alan Kurdi mentions / week 1 month after mentions / week mentions / week 0 Syrian Refugee conversation Alan Kurdi

59 BEFORE & AFTER PARIS ATTACKS Press articles claiming that one of the attackers had a Syrian passport could ve impacted the sentiment France (and Parisians in particular) had towards Syrian refugees in their countries. However, people were wary of accepting this until there was concrete evidence. In fact, France s negative sentiment towards Syrian refugees actually decreased, with positive sentiment increasing by almost 10%! Negative 16.7% Positive 30.8% Negative 9.5% Positive 40.5% BEFORE AFTER Neutral 52.5% Neutral 50.0%

60 MOST NEGATIVE ABOUT PARIS ATTACKS THE TRUMPETS 28.8% of Americans had negative sentiment towards Syrian refugees after the Paris attacks in November Majority of this conversation was driven by Trump supporters.

61 BRINGING IT ALL TOGETHER

62 12/29/2014 1/12/2015 1/26/2015 2/9/2015 2/23/2015 3/9/2015 3/23/2015 4/6/2015 4/20/2015 5/4/2015 5/18/2015 6/1/2015 6/15/2015 6/29/2015 7/13/2015 7/27/2015 8/10/2015 8/24/2015 9/7/2015 9/21/ /5/ /19/ /2/ /16/ /30/ /14/ /28/2015 1/11/2016 1/25/2016 2/8/2016 2/22/2016 3/7/2016 3/21/2016 4/4/2016 4/18/2016 5/2/2016 5/16/2016 5/30/2016 6/13/2016 6/27/2016 7/11/2016 7/25/2016 8/8/2016 8/22/2016 9/5/2016 9/19/ /3/2016 OVERALL VOLUME OF CONVERSATION 1,800,000 Bombing of aid trucks 1,600,000 1,400,000 1,200,000 1,000, , , ,000 Alan Kurdi Paris attacks #IamSyrian campaign Omran Daqneesh 200,000 0

63 OVERALL CAMPAIGN ANALYSIS Human-centred stories continue to appeal to emotions of citizens around the world and compel them to share these stories. People are drawn to narratives around the individual, particularly children. Public outcry is most pronounced in 24hrs after an event. Knowing when this moment occurs can help better leverage this outcry for change. Impactful photos or short videos appear to have the greatest impact and are shared prolifically.

64 WOMEN IN REFUGEE CAMPS: MAY JULY 2017

METHODOLOGY Mentions from 1 Jan 2016 19 May 2017 Thematic Analysis: 1 Feb 2017-19

65 METHODOLOGY Mentions from 1 Jan May 2017 Thematic Analysis: 1 Feb May k mentions about refugees 400 k unique authors (0 4 credibility rating)

66 METHODOLOGY Collected mentions in English Mentions were collected from over 25 different countries

OVERVIEW Contributors to conversation about refugee camps

residing in or formerly resided in refugee camps.

7% of all conversation, whereas female authors

* Male Unknown Female Conversation about Calais refugee

There was also conversation about initiatives by refugees

67 OVERVIEW Contributors to conversation about refugee camps ranged from the general refugee population to those residing in or formerly resided in refugee camps. Male authors contributed to 34.7% of all conversation, whereas female authors contributed 16.9%.* Male Unknown Female Conversation about Calais refugee camp kitchens, volunteers and the wellbeing of children. There was also conversation about initiatives by refugees within camps as well as about the conditions of Greek camps. 17% 35% Similar to female conversation, but with the addition of engagement with political discourse about the refugee crisis, with particular reference to Palestinians. 48% *Where gender could be determined.

COUNTRY BREAKDOWN Conversation by country over data collection period UK: 71 922

68 COUNTRY BREAKDOWN Conversation by country over data collection period UK: Germany: Canada: USA: Syria: 851 Egypt: Turkey: India:

69 RAPE AND VIOLENCE In the first week of February conversation spiked due to rising concerns about the violence and rape perpetrated against women. The conversation focused primarily on cases in Germany and Britain s Dunkirk refugee camp which would have a fire in April resulting in the displacement of refugees /30/2017 2/28/2017 3/31/2017 4/30/ Conversation (excl. rape) Rape

70 SYRIA CONVERSATION Conversation within Syria Aleppo 2 Homs 2 Conversation about Syria

71 The Magic in the Machines Understanding public sentiment towards a company, organisation, person or event is useful information. Understanding the detail of the topics that are driving that sentiment is social intelligence that can manage risk and guide strategic decision-making.

72 COLIN

LESSONS LEARNED FROM THE 2016 ELECTION

LESSONS LEARNED FROM THE 2016 ELECTION IE 561 Continuous Quality Improvement of Process Fall 2016 Cameron MacKenzie Most of this information comes from the website 538 IE 561 CONTINUOUS QUALITY IMPROVEMENT