social media analytics - university of minnesota -...

Social Media Analytics

1


Ahmed Abbasi

University of Virginia

1

Outline

� Social Media Overview

� Social Media for Communication and Collaboration

� Social Media Analytics

� Application areas

� Challenges

� Social Media for Engagement2


2

Social Media

� Socialnomics video:

3

The Social

Ecosystem

4

Collaboration

Analytics

Engagement

Source: Forrester Research


3

SOCIAL MEDIA FOR

COMMUNICATION AND

COLLABORATION

5

Communication and Collaboration:

Social Media Usage

Source: McKinsey Quarterly 2012


4


Benefits for Internal Use

7

Source: McKinsey Quarterly 2012


Alternative to Email?

� French company Atos to ban internal email usage.

� Statistics:

� 200 emails per employee, per day

� 10% are useful

� 18% are spam

� Exploring other tools, including social media

8

Source: ABC News, 2011


5


Challenges

� Social media management policies

� Security

� Usage

� 75% of employees use social media to stay in touch with friends

� Technology portfolio management

� On average, 6 social media tools

� Some using 25+ tools!

� Unified communication (UC) 9

SOCIAL MEDIA ANALYTICS

10


6

Social Media Analytics Definition

�Technology used to monitor, measure, and analyze activity by users of the Web 2.0 framework to provide information to make business decisions.

� According to a 2011 Bloomberg Businessweek Survey:

Gartner’s Hype Cycle for Analytics

Source: Gartner 2011

Social Analytics

Social Network Analysis

Emotion Detection

Social Media Monitoring

Social Media Metrics


7

Text Information Categories

13

Low HighIdentification Complexity

Topics Opinions Emotions Events

Multi-class problemKeyword-driven

Series of binary or multi-class problems

Multi-class problemOverlapping classes

Multi-class problemContext dependent

ComplexitiesLinguistic featuresLiterary devices (sarcasm, satire, rhetoric, irony, etc.)Spam Context

Social Media Analytics: Opinion Mining

14

Source: Chen 2010


8

Social Media Analytics: Opinion Mining

15

Source: Chen 2010

ONLINE SENTIMENTS AND

FINANCIAL PERFORMANCE

16


9

Sentiment Indicators and Indexes

� Consumer sentiment as an indicator?

� Consumer Confidence Index (CCI),

� Consumer Sentiment Index (CSI), etc.

� Web 2.0: Social Media Sentiment?

Online Customer Satisfaction

February 12, 2005 September 25, 2010

2/2008Shutterfly Gallery

2007-2008Photo BooksNow, free unlimited storage space

4/2009iPhone App

Sources: Foresee, http://www.foreseeresults.com, CNN Money, http://tech.fortune.cnn.com/2009/10/07/shutterfly-fights-the-photo-recession/Internet Archives, http://www.archive.org/


10

Online Customer Satisfaction

19Increased satisfaction score between 2009 and 2011 also resulted in increased stock price.

Social Media Sentiments as an Indicator?

20

The strong relationship between stock price and sentiment polarity/intensity (sents) for Apple over a 24-hour period.

Source: Das 2010


11

Using Blogs to Predict Movie Sales

� Key finding: frequency of positive sentiments is better indicator than volume of posts alone.

� Relationship between movie income per theater (solid line) for new releases, and frequency of positive blog posts (dashed line).

21

Using Twitter to Predict DJIA Movements

2286.7% accuracy in predicting closing up and down of DJIA using Twitter tweets

Source: Bollen et al. 2010


12

Twitter and the Facebook IPO

23

Social Media Analytics: Twitter

�Twitter

�100M+ active users per month

�50% log on every day

�55% on mobile

�1B Tweets every 3 days� 10 billion/month in Oct. 2012

� 6 billion/month in Sept. 2011

� 4 billion/month in Mar. 2011

� 3 billion/month in Jan. 2011

� 2 billion/month in Apr. 2010

� 1 billion/month in Jan. 201024


13

Social Media Analytics: Twitter

25

Source: http://www.mediabistro.com/alltwitter/api-billionaires-club_b11424

USING SOCIAL MEDIA FOR

DECISION-MAKING

26


14

Social Media and Product Design:

The Case Of The Red Dell

Source: Radian 6, 2010

Social Media and New Logos:

Mind the Gap?

� 2,000+ critical comments on Facebook

� 5,000+ new critical followers on Twitter

� 14,000+ parodies of the new logo

� Gap reverted back to the old logo within days

28

Source: The Guardian 2010


15

Social Media for M&A Analytics

29

Source: Lau et al. 2012

Social Media for Early Warnings: ADRs

30


16


� Current warning mechanisms

� Some problems:

� Might not be enough reported incidents

� Can take time

� Differences in time of warning for various drugs of the same class

� Social Media may provide early warning…

31


32

s

v

u

Time t

Time t

Time t

FDA 0

Approval

FDA 1

Black Box

Change1

FDA 2

Black Box

Change2

FDA 3

Withdrawal

Sentiments

S(t)

Volume

V(t)

Search Query

U(t)

0

0

0


17


33


34


18

Social Media Analytics: Tiger Case

� Why did Nike maintain its relationship with Tiger Woods?

� Why did Accenture part with Tiger Woods?

� Answer: Social Media Analytics

35


� Sentiment for Tiger Woods before and after scandal

� Combined from Twitter, blogs, forums, social networking sites, etc.

36

Source: Xenophon Strategies, 2010


19


� Discussion keywords in Tiger conversations post scandal

� 4% - 7% of the postings mention a sponsor

37



� Far greater reference to Tiger in Accenture conversations than Nike

38



20


� Sentiment for Accenture within Tiger Woods conversations

39



� Sentiment for Accenture within Tiger Woods conversations after cutting ties with Tiger

40



21


� Sentiment for Nike within Tiger Woods conversations

41



� 2010 CMU study on Economic Impact of Nike sticking with Tiger:

� $1.6 million higher revenue in golf ball sales alone (in 2010) due to sustained relationship

� “Tiger’s continued endorsement profitable for Nike, but perhaps not for non-golf related products”

42


22

SOCIAL MEDIA ANALYTICS:

CHALLENGES

43

Challenges: Spam

� Webpages (web spam) – 20%

� Our research: 70%-80% of the top 100 Google search results for “online pharmacy” in 2009-2011 were spam.

� Blog spam (splogs) – 12%

� User-generated comments to blogs > 50%

� Some studies report rates as high as 90%!

� Twitter – between 5% and 10%

� Our research: varies, depending on topic44

Sources: Akismet 2012; Websense 2010; Choi et al. 2011


23

Challenges: Spam – Websites and Blogs

45

Source: Abbasi et al. 2012

Challenges: Spam - Reviews

46

Sources: Ott et al. 2012


24

Challenges: Spam - Detection

� Spam Cues:

� Lengthier

� Higher average word length

� More descriptive and vivid

47

Sources: Ntoulas et al. 2006; Ott et al. 2011

Challenges: Sentiment Accuracy

� Analyzed performance of several SaaSopinion mining options:

� Found that many of the tools had overall accuracies as low as:

� 42% for sentiment polarity classification

� 75% for within-one accuracy

� In comparison, baseline ML methods:

� 73% for sentiment polarity classification

� 98% for within-one accuracy48


25

Challenges: Context…the “why”

� According to the 2011 Gartner Hype Cycle:

� Existing text and social media analytics tools tend to focus on the semantic dimension of language: what people are saying.

� While using such tools organizations have difficulty understanding discussion context and participants’ actions and underlying intentions.

49

Sources: Gartner 2011


� A Text Analytics Framework for Sense-making

50


26


51

Manufacturers can develop new products.

Try to develop new products. But I think that manufacturers must invest funds to do academic research.

What new product we can try?

We can try to develop new flavors of products

The research and development cannot be finished in one or two day. Now it must face surplus.

New products with health care function

We can develop different products according to different consumer groups. Such as tea with health function

Currently, milk tea is popular. We can produce more milk tea.

Packaging milk tea seems impossible.

If developed milk tea poured many times, it might attract more customers.

In consider of sales, we can think about seller, promotion mode, brand culture and propaganda.

Yeah, manufacturers cannot bear the cost of research and development.

Training and recruiting the marketing person，For sales Jumping to a big sale can be effective?

Tea bag can be poured repeatly?

I think milk tea can be poured repeatly hasn't any practical implication.？big sale will lose money

Making some promotional activities.

building the brand concept is pretty important. I think there no famous band in tea bag market.

So, we can create our brand though donation.

we can find some famous spokesmen.

We heard people donate quilt and tents, but didn't hear donating tea bag. Donation CANNOT promote the brand.

what kind of spokesperson will contribute to propaganda of tea bag?

Spokesperson with positive image and effect is very important. So, they can play good publicity effect？How to deal with excess productivity How about outsourcing?

Big sale is not appropriate. We need to make money and this sales model is failure.

Outsourcing the excess productivity.

Too much inventory will waste the charges of the stock. Sales might let more consumers to know our brand.

Outsourcing is work for others and brings in a little labor cost. It just reuse the excess productivity.

Who is outsourcer?

And then other people generate bias to our brand. It is CANNOT change such bad impression.

Once our brand sold very cheaply, it is hard to rise in price.

So, it cannot make such big sales. This pattern will hurt the brand building.

Well, yeah, let's think about the others marketing strategy.

Discussion: Tea bag manufacturer's dilemmaThen the development of new product has certain theory and factual basis.

to older man, slimming tea to young woman, and packaging milk tea.

Discussion: Tea bag manufacturer's dilemma☆☆☆☆ Manufacturers can develop new products.

Try to develop new products. But I think that manufacturers must invest funds to do academic research.

? What new product we can try?☆☆☆☆ New products with health care function☆☆☆☆We can try to develop new flavors of products

The research and development cannot be finished in one or two day. Now it must face surplus.

yeah, manufacturers cannot bear the cost of research and development.☆☆☆☆ We can develop different products according to different consumer groups. Such as tea with health function☆☆☆☆Currently, milk tea is popular. We can produce more milk tea.

Packaging milk tea seems impossible.

?Tea bag can be poured repeatedly?☆☆☆☆If developed milk tea poured many times, it might attract more customers.

I think milk tea can be poured repeatedly hasn't any practical implication.☆☆☆☆ In consider of sales, we can think about sale, promotion mode, brand culture and propaganda.☆☆☆☆ Training and recruiting the marketing person☆☆☆☆ ，For sales Jumping to a big sale can be effective

? ？Big sale will lose money

Big sale is not appropriate. We need to make money and this sales model is failure.☆☆☆☆Making some promotional activities.

Building the brand concept is pretty important. I think there no famous band in tea bag market.☆☆☆☆ So, we can create our brand though donation.

We heard people donate quilt and tents, but didn't heard donating tea bag. ☆☆☆☆ So, we can create our brand though donation

? What kind of spokesperson will contribute to propaganda of tea bag?

Spokesperson with positive image and effect is very important. So, they can play good publicity effect☆☆☆☆ Too much inventory will waste the charges of the stock. Sales might let more consumers to know our brand.

And then other people generate bias to our brand. It is CANNOT change such bad impression.

Once our brand sold very cheaply, it is hard to rise in price.

So, it cannot make such big sales. This pattern will hurt the brand building.

Well, yeah, let's think about the others marketing strategy.

? ？How to deal with excess productivity How about outsourcing?☆☆☆☆ Outsourcing the excess productivity.

Outsourcing is work for others and bring in a little labor cost. it just reuse the excess productivity.

? Who is outsourcer?

Then the development of new product has certain theory and factual basis.

to older man, slimming tea to young woman, and packaging milk tea.

Donation CANNOT promote the brand.

SOCIAL MEDIA FOR

CUSTOMER ENGAGEMENT

52


27

Social Media Sources and Control

53

Source: Foresee 2010

Online Social Media Usage

� A 2010 study of 99 franchisors’ web presence revealed:

54

Source: One Up Web 2010


28

Online Social Media Usage

55

Source: One Up Web 2010

The Conversion Funnel: e-Tailer

56


29

The Conversion Funnel: Social Media

57

Source: Peter Chang, http://webpersonas.blogspot.com/2011/01/deep-dive-into-social-media-conversion.html

SMR Study: How to get Retweeted

� 25% follow a brand

� 67% purchase from the brand they follow

58

Source: Malhotra et al. 2012

What Doesn’t Work

Asking questions

Hashtags

Embedding links

Contests

What Works

Leaving room

Making it relevant/timely

Providing practical information

Offering deals

Creating anticipation


30

?

59

social media analytics - university of minnesota -...

Documents