Sentiment in Social Media: The Genie in the Bottle

Sentiment in Social Media: The Genie in the

Bottle

Seth GrimesAlta Plana Corporation

301-270-0795 -- http://altaplana.com -- @sethgrimes

Monitoring Social Media -- BostonOctober 5, 2010

Sentiment in Social Media

3

Three assertions:1.Human

communications, online & off, are inherently subjective.

2.Online facts & opinions have business value.

3.Opinion often masquerades as Fact.

Sentiment in Social Media

4

Facts and FeelingsThe unemployment rate is 9.7%.

Unemployment is WAY TOO HIGH!!

The unemployment rate is higher than it was two years ago (5.1%).

Former U.S. Federal Reserve Chairman Alan Greenspan said on Tuesday that the global recession will "surely be the longest and deepest" since the 1930s, adding that the Obama administration's Troubled Asset Relief Program will be insufficient to plug the yawning financial gap. [Reuters, Feb 18, 2009] [underlining added]

Bernanke is doing a better job than Greenspan.

www.google.com/publicdata

Sentiment in Social Media

7

Questions for business & government:What are people saying? What’s hot/trending?

What are they saying about {topic|person|product} X?

... about X versus {topic|person|product} Y?

How has opinion about X and Y evolved?

How has opinion correlated with {our|competitors’|general} {news|marketing|sales|events}?

What’s behind opinion, the root causes?• (How) Can we link opinions &

transactions?• (How) Can we link opinion & intent?

Who are opinion leaders?

How does sentiment propagate across multiple channels?

Sentiment in Social Media

8

Information access w/structure, sentiment:

Sentiment+

Sentiment

User intent?

Sentiment in Social Media

9

“In this example, you can quickly see that the Drooling Dog Bar B Q has gotten lots of positive reviews, and if you want to see what other people have said about the restaurant, clicking this result is a good choice.”

-- http://googleblog.blogspot.com/2009/05/more-search-options-and-other-updates.html

“In the recap of [Searchology] from Google’s Matt Cutts, he tells us that: ‘If you sort by reviews, Google will perform sentiment analysis and highlight interesting comments.’

-- Bill Slawski, “Google's New Review Search Option and Sentiment Analysis,” http://www.seobythesea.com/?p=1488

Sentiment in Social Media

11

For better information access, understand user intent.

User intent?

Sentiment in Social Media

12

We have a decision support need. We=

Consumers

Marketers

Competitors

Managers

Decision support requires tools beyond general-purpose search/information access…

Sentiment in Social Media

13

Counting term hits, in one source, at the doc level, doesn’t take you far...

Good or bad? What’s behind the posts?

Sentiment in Social Media

14

Counting -- clicks, not even keywords -- leaves you wondering Why? and So What?

Sentiment in Social Media

15

“Sentiment analysis is the task of identifying positive and negative opinions, emotions, and evaluations.”

-- Wilson, Wiebe & Hoffman, 2005, “Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis”

“Sentiment analysis or opinion mining is the computational study of opinions, sentiments and emotions expressed in text… An opinion on a feature f is a positive or negative view, attitude, emotion or appraisal on f from an opinion holder.”

-- Bing Liu, 2010, “Sentiment Analysis and Subjectivity,” in Handbook of Natural Language Processing

Sentiment in Social Media

16

Sentiment analysis turns attitudes into data.

Ingredients:Structured and unstructured sources.Subjectivity – WW&H used over 8,000 clues.

Polarity: positive, negative, (both,) or neutral.• Other classifiers?

Intensity.

Sentiment in Social Media

17

There are many complications. Simplified:

Sentiment may be of interest at multiple levels.

Corpus / data space, i.e., across multiple sources.

Document.Statement / sentence.Entity / topic / concept.

Human language is noisy and chaotic!Jargon, slang, irony, ambiguity, anaphora,

polysemy, synonymy, etc.Context is key. Discourse analysis comes into

play.Must distinguish the sentiment holder

from the object: Greenspan said the recession will…

Sentiment in Social Media

18

Sentiment sources (broadly):NewsSocial mediaEnterprise feedback

(To me, it’s all social.)Consumption models:

1. General search engine2. Siloed/vertical search interfaces, a.k.a.

monitoring tools3. Application embedded4. Widgets/gadgets

Rated negative?

???

Manual focus

Sentiment in Social Media

22

An accuracy aside: [WWH 2005] describes an inter-annotator agreement test.10 documents w/ 447 subjective expressions. The two annotators agree on 82% of cases.

Excluding of uncertain subjective expressions (18%) boosts agreement to 90%.

(Wilson, Wiebe & Hoffman, 2005, “Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis”)

Sentiment in Social Media

23

Claim: You fall far short with (only) --Doc-level analysis: • Need to look at features, opinion holders.

Keyword-based analysis.• Need semantics.

Human-only analysis.• Need the power of machines.

Machine-only analysis.• Need the sensitivity of humans.

“Reading from text in general is a hard problem, because it involves all of common sense knowledge.”

-- Expert systems pioneer Edward A. Feigenbaum

Sentiment in Social Media

24

Next slides have a few more examples.

SAS Social Media Analytics.Clarabridge Social Media Analysis.Crimson Hexagon VoxTrot.Clarabridge sentiment analysis.A Jodange embeddable “gadget.”Newssift.com, a now defunct media

portal from the Financial Times Group.

Sentiment in Social Media

29

Sentiment in Social Media

31

Beyond polarity: “We present a system that adds an emotional dimension to an activity that Internet users engage in frequently, search..”

-- Sood & Vasserman & Hoffman, 2009, “ESSE: Exploring Mood on the Web”

Sentiment in Social Media

32

Happy Sad AngryEnergetic ConfusedAggravatedBouncy Crappy AngryHappy Crushed BitchyHyper Depressed EnragedCheerful Distressed InfuriatedEcstatic Envious IrateExcited Gloomy Pissed offJubilant GuiltyGiddy IntimidatedGiggly JealousLonelyRejectedSadScared

-----------------------The three prominent mood

groups that emerged from K-Means Clustering on the set of LiveJournal mood labels.

Sentiment in Social Media

34

Questions?

Comments?