Social text sentiment and tone analysis [aai 201] - (4160)
-
Upload
ruben-pertusa-lopez -
Category
Technology
-
view
1.033 -
download
5
Transcript of Social text sentiment and tone analysis [aai 201] - (4160)
April 10-12 | Chicago, IL
Social Text, Sentiment and Tone AnalysisAdvanced Analytics and Insights
Ruben Pertusa Lopez, SolidQ, Business Intelligence DPE & MAP 2013 ([email protected])
Paco Gonzalez, SolidQ, Mentor ([email protected])
April 10-12 | Chicago, IL
Please silence cell phones
Paco & Ruben
• Conference Speakers
• Based in Europe
• Book Authors
• PHD Candidate on Data Mining
• Project Managers
• Microsoft Certified Professionals
3
Goals
• This session will help us understand how to analyzesentiment / tone using cutting edge Microsoft Technologies
• This is NOT a research session on NLP (Natural LanguageProcessing). Don’t be scared! ☺
4
Agenda
• Overview of Sentiment Analysis
• Gathering and Storing Data
• Sentiment Analysis Techniques
• Business Analytics for Sentiment & Structured data,
together
5
April 10-12 | Chicago, IL
Overview of SentimentAnalysis
What is Sentiment?
Feelings, Opinions, Emotions
• Like
• Dislike
• Good
• Bad
• …
7
Some examples
8
paulo @paulomors
Barcelona Beating Milan 4-0 and a gallon of Coke, best day of the year ☺
αυѕтιη ✰✰✰✰ @AustinJohnsto
A 2 hour delay is like when a restaurant only has Pepsi products. It'll work but ill still be very disappointed.�
Trace @trace_haf
Drinking more Coke than water every day does no good for you health.
DONALD @donald150
My budget decides whether coke or pepsi, always buy the cheaper
☺☺☺☺
����
☺☺☺☺?����?����
Not only Twitter!
9
The Walking Dead Season 3 (3300 customer reviews)
Awesome season opener! October 15, 2012 By K. Erwin
After sticking through season two, which was alot of looking for a little girl and standing around on a farm waiting for something to happen, I hoped that they'd pick up the pace a little with season three. The premiere doesn't dissapoint!
The Walking Dead Season 3 Mid-Premiere (72K Likes, 7K comments)
Timothy Berteau You guys are crazy. One boring episode and you think the show sucks, did you forget how awesome the two episodes before it were? Not every episode isgoing to be action packed. Season 1 and 2 had some very boring moments as well.
18 February at 00:58 via mobile · 5 likes
DEMOLooking at some Twitter Sentiment
10
Surrounded by opinions
11
12 Tbday
21 PbHadoopcluster
7 PbMonth
(search queries info)
1 TbTweets
day
75 MiScores
day
Millions of opinions
4 BGraph
edg/day
7 TbData day
Valuable Information for our Business
Questions
• Is this review positive or negative?
• Do this Twitter User like or dislike my new show?
• What are they saying about our company or services?
• How are Facebook User’s Attitudes about the next
election?
12
Is that the only valuable info?
What is Sentiment Analysis?
Text Categorization (Opinion Mining)
• Positive / Negative / Neutral
• 1, 2, 3, 4, 5 Stars
• For / Against
13
TextSentiment Analysis
TechniquesCategoryIN
Photos
Videos, etc.
OUT
DEMOTwitter for Analytics
14
April 10-12 | Chicago, IL
Gathering and Storing Data
Gathering data from sources
Public/Private APIs
• Limitations
• Privacy
• Format & Structure of source data
• Updates
Webcrawlers? Call the cops! �
16
How may it look?
JSON Example (1 tweet)
17
Storing the gathered data
Why?• Valuable data!
• Store now. Figure out later
How?• Structured (Relational Database – SQL Server)
• Semi-Structured (Hadoop Cluster – Microsoft HDInsight)
18
Doctor, We need some help
The 4 V’s
19
Volume
Velocity
Variety
Variability
Doctor, We need some help
The 4 V’s
20
Volume
Velocity
Variety
Variability
Start building our system
21
ExtractTransform
Load
ExtractLoad
DEMOLet’s gather some Twitter data ☺
22
April 10-12 | Chicago, IL
Sentiment AnalysisTechniques
Understanding the problem
Identify relevant parts
• Nouns
• Adjectives/Adverbs
• Verbs
Drop anything else
24
Data != Sentiment Data
Sentiment Analysis Techniques
Techniques• Natural Language Processing
• Basic Statistics• Clustering
• Fuzzy Components
• Classification
• Estimation
ToolsHDInsight, SSIS, SSAS DM, FullText Search (Semantic Search)
25
Dictionaries
Match words
“Coke is the best & coolest drink on the market”
Some Other Database Example
SentiWordNethttp://sentiwordnet.isti.cnr.it/
26
Tone Index DictionaryPositive 10 amazingPositive 9 awesomePositive 8 bestPositive 7 excellentPositive 6 excitingPositive 5 greatPositive 4 goodPositive 3 rocksPositive 2 coolPositive 1 :)Neutral 0Negative -1 :(Negative -2 poorNegative -3 badNegative -4 criticized Negative -5 attacked Negative -6 humiliatedNegative -7 sucksNegative -8 terribleNegative -9 horribleNegative -10 worthless
A closer look at the example
27
Tone Index DictionaryPositive 10 amazingPositive 9 awesomePositive 8 bestPositive 7 excellentPositive 6 excitingPositive 5 greatPositive 4 goodPositive 3 rocksPositive 2 coolPositive 1 :)Neutral 0Negative -1 :(Negative -2 poor
“Coke is the best & coolest drink on the market”
Fuzzy Match
“Best” matches “best” =+ 8
“coolest” matches “cool” =+ 2
Total = + 10
☺☺☺☺
DEMOGive me your sentiment!
28
Sentiment Analysis Challenges
Phrase level polarity
• “The US fears happy caffeine consumers”.
Context polarity
• Context: The date that Steve Jobs died.
• Opinion 1: “This is the worst day of my life”.
• Opinion 2: “The world is a better place today”.
Irony, Sarcasm, Irregular forms, Pragmatic information…
29
It looks like…
30
ExtractTransform
Load
ExtractLoad
SA Techniques
☺ � �
April 10-12 | Chicago, IL
Combining SentimentAnalysis with StructuredData
MORE Valuable Information for ourBusiness
Questions• Is this positive/negative review affecting my sales?
• Have we increased our sales because of positive tweets? Can we learn anything from opinions to improve our products?
• How are people responding to this campaign?
32
Bring our cubes into a new world
New ways of analysis
Better decisions
• Drive next campaign, new wave of products, etc.
Estimate future figures
33
☺ � � +
DEMOOur cubes have feelings ☺
34
Final picture
35
ExtractTransform
Load
ExtractLoad
SA Techniques
☺ � � +
Brief Summary
During this session..• Business Insights from social opinions
• Sentiment Analysis loves Big Data ☺
• Microsoft Technologies can help us with some SA Techniques
• There is a huge competitive advantage by using Sentiment Analysis
36
QUESTIONSPositive / Negative / Neutral ones ☺
37
Contact us!
Rubén Pertusa López ([email protected])
@rpertusaData Platform Engineer, SolidQ
Microsoft Active Professional 2013
Paco González ([email protected])
@pacosqlMentor, SolidQ
38
Win a Microsoft Surface Pro!
Complete an online SESSION EVALUATION to be entered into the draw.
Draw closes April 12, 11:59pm CTWinners will be announced on the PASS BA Conference website and on Twitter.
Go to passbaconference.com/evals or follow the QR code link displayed on session signage throughout the conference venue.
Your feedback is important and valuable. All feedback will be used to improve and select sessions for future events.
April 10-12, Chicago, IL
Thank you!Diamond Sponsor Platinum Sponsor