sentiment analysis symposium 2010, welcoming address, seth grimes

18
Sentiment Analysis Symposium Seth Grimes Alta Plana Corporation 301-270-0795 -- http://altaplana.com April 13, 2010

Upload: sentiment-analysis-symposium

Post on 26-Jan-2015

104 views

Category:

Technology


1 download

DESCRIPTION

A review of sentiment analysis challenges and themes, introducing the 2010 Sentiment Analysis Symposium, presented by symposium organizer Seth Grimes.

TRANSCRIPT

Page 1: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

Seth GrimesAlta Plana Corporation

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

April 13, 2010

Page 2: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

2

WiFi:Username: risingmedia

Password: 12345

Hashtag: #SAS10

Page 3: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

3

Two assertions:

Human communications are inherently subjective.

Opinion often masquerades as Fact.

Page 4: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

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]

Benjamin Bernanke is doing a better job than Greenspan.

www.google.com/publicdata

Page 5: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

5

We have a decision need, for monitoring, measurement, and analysis that support action.

We =Consumers

Marketers

Managers

Competitors

Government

Politicians

Page 6: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

6

Questions...What are people saying? What’s hot?

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

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

How has opinion about X and Y trended/evolved?

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

What’s behind opinion, the root causes?

Who are opinion leaders?

How does sentiment propagate across multiple channels?

Page 7: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

7

Attention to sentiment is not new.

Page 8: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

8

Methods are. Yet counting term hits, in one source, doesn’t take you far.

Good or bad? What’s behind the posts?

Page 9: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

9

Beyond counting: “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”

Ingredients:Structured and unstructured sources.Subjectivity.Polarity.Intensity.

Page 10: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

10

There are many complications. Simplified:

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.Sentiment holder ≠ object:

Greenspan said the recession will…

Page 11: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes
Page 12: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes
Page 13: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

13

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

Page 14: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

14

Putting aside benefits of automation, how can machine accuracy approach human sensitivity?

Claim: You fall short with (only) --Doc-level analysis.Keyword-based analysis.

You need strong natural language processing (NLP).

You can also boost accuracy by, for example, ...

Page 15: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

15

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.

Page 16: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

16

Text + ratings & classification:

Page 17: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes
Page 18: Sentiment Analysis Symposium 2010, welcoming address, Seth Grimes

Sentiment Analysis Symposium

18

The symposium...