Whose and What Chatter Matters? The Effect of Tweets on Movie Sales - - PowerPoint PPT Presentation

▶
whose and what chatter matters the effect of tweets on
SMART_READER_LITE
LIVE PREVIEW

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales - - PowerPoint PPT Presentation

Feb 05, 2024 44 likes •294 views

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Huaxia Rui (joint work with Yizao Liu, and Andrew Whinston) Simon School of Business University of

slide-1
SLIDE 1

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales

Huaxia Rui (joint work with Yizao Liu, and Andrew Whinston)

Simon School of Business University of Rochester

October 6, 2012

1 / 25

slide-2
SLIDE 2

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters?

Outline

1 Whose and What Chatter Matters?

Motivations Data Model Results TwitterSensor

2 / 25

slide-3
SLIDE 3

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters?

Word-of-Mouth (WOM) Research

Word-of-mouth is often considered to be the most credible information source to consumers for the purchase of a new product

  • r new service.

Offline period ( before 2003) Online period ( since 2004) Big Data period ( present )

3 / 25

slide-4
SLIDE 4

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters?

The Effect of WOM on Product Sales

. Awareness effect vs. Persuasive effect . . . . . . . . Awareness effect: the function of spreading basic information about the product among the population. Persuasive effect: the function of altering people’s preferences toward the product and thus influencing their purchase decisions.

4 / 25

slide-5
SLIDE 5

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Motivations

Motivation 1

. What Chatter Matters: the Good, the Bad, or the Eager? . . . . . . . . “back at work and recovering from #avatar - fantastic movie!” “I’m just not excited about the new Alice In Wonderland :/ Tim Burton seems to be running out ideas a bit” “DAMN IT!!! Didn’t make it...Sold out tickets for Avatar!!!”

5 / 25

slide-6
SLIDE 6

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Motivations

Motivation 2

. Whose Chatter Matters? . . . . . . . . “Today a single customer complaint from someone with influence can have more impact on your company’s reputation than your best marketing.” – Jason Duty, head of Dell’s global social

  • utreach service. 1

1Source: Customer must be king in the web world, Financial Times. 01/25/2012 6 / 25

slide-7
SLIDE 7

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Motivations

Motivation 2

. The Million Followers Fallacy? . . . . . . . . “The number of Twitter followers (or reach) is usually meaningless.”

a

“Indegree alone reveals very little about the influence of a user.”

b

Per Christakis’ anecdotal evidence, Twitter follower/Facebook friend counts are misleading.c Recently, Evan Williams hinted that a simple measure of followers“doesn’t capture your distribution”and follower counts may soon become the second most important number to users.

aAvnit, A. (2009), Berinato, S. (2010) bCha, Haddadi, Benevenuto, and Gummadi (2010) cGarber, M. (2010) 7 / 25

slide-8
SLIDE 8

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Why Twitter WOM data?

Twitter is a more natural environment to study the awareness effect of WOM (push vs. pull). More social network information is available from Twitter. A new category of WOM: intention WOM. Volume: 4 million tweets about 63 movies.

12,136 posts used in Liu (2006). 95,867 posts used in Duan, Gu, and Whinston (2008).

8 / 25

slide-9
SLIDE 9

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Data

Daily box office revenue data from BoxOfficeMojo.com Tweets from twitter.com collected through Twitter Application Programming Interface (API).

Each tweet: content, time, number of followers. Pre-processing: advertising tweets, irrelevant tweets. Tweet classification: intention tweets, positive tweets, negative tweets, neutral tweets.

9 / 25

slide-10
SLIDE 10

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Tweet Classification

10 / 25

slide-11
SLIDE 11

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Intention Classifier

. Pattern Matching . . . . . . . . (plan|need) (to|2) (watch|see|c|catch)( the)* movie (sold|sell) out|no ticket saw|watched|went just really last ... . SVM . . . . . . . . Decision function: f (x) = ∑

i αiK(xi, x) + b

RBF Kernel: K(x, x′) = exp(−γ||x − x′)||2)

11 / 25

slide-12
SLIDE 12

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Sentiment Classifier

. Naive Bayesian Approach . . . . . . . . C ∗ = argmaxCiP(Ci|D) P(Ci|D) = P(D|Ci)P(Ci) P(D) , P(D|Ci) =

j=n

∏

j=1

P(tj|Ci) P(tj|Ci) = Nij + α Ni + 2α α: smoothing factor Nij: number of tweets in class i containing word j. Ni: number of tweets in class i.

12 / 25

slide-13
SLIDE 13

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Data

Variables

Gross Revenues Movie gross box office revenues from Friday to next Thursday Ad Advertising expenditure in a week Tweets Total number of tweets mentioning the name of the movie i in a week (i.e., from this Friday to next Thursday) Type-1 tweets Total number of tweets with followers less than 400 (small audiences) from Friday to next Thursday Type-2 tweets Total number of tweets with followers more than 400 (large audiences) from Friday to next Thursday T2Ratio Ratio of Type-2 tweets in a week IntRatio (%) Ratio of intention tweets in a week PosRatio (%) Ratio of tweets with positive sentiment in a week NegRatio (%) Ratio of tweets with negative sentiment in a week

13 / 25

slide-14
SLIDE 14

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Model

Dynamic Panel Data Model

yit = αyi,t−1 + β′xi,t−1 + ηi + νit (1) Revenueit = αRevenuei,t−1 + β0Adi,t−1 + β1Tweetsi,t−1 + β2T2Ratioi,t−1 + β3IntRatioi,t−1 + β4PosRatioi,t−1 + β5NegRatioi,t−1 + ηi + νit (2)

14 / 25

slide-15
SLIDE 15

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Model

Estimation

(yit −yi,t−1) = α(yi,t−1 −yi,t−2)+(xi,t−1 −xi,t−2)′β +(νit −νi,t−1) ¯ yit = α¯ yi,t−1 + β′¯ xi,t−1 + ¯ νit (3) where ¯ yit = yit − yi,t−1 ¯ xi,t−1 = xi,t−1 − xi,t−2 ¯ νit = νit − νi,t−1.

15 / 25

slide-16
SLIDE 16

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Model

Estimation

To estimate δ = (α, β′)′, we use yi1, · · · , yi,t−2, xi1, · · · , xi,t−2 as instruments for movie i, period t.

¯ Xi =    ¯ yi,2 ¯ xi,2 . . . . . . ¯ yi,T−1 ¯ xi,T−1    , ¯ Yi =    ¯ yi,3 . . . ¯ yi,T    , Zi =      yi,1 xi,1 ... ... ... yi,1 yi,2 xi,1 x1,2 ... ... ... . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ... yi,1 ... yi,T−2 xi,1 ... xi,T−2      .

16 / 25

slide-17
SLIDE 17

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Model

Estimation

The GMM estimator minimizes the criterion J = [ N ∑

i=1

Z ′

i ( ¯

Yi − ¯ Xiδ) ]′ W [ N ∑

i=1

Z ′

i ( ¯

Yi − ¯ Xiδ) ] (4) where W is the weighting matrix and δ = (α, β′)′ is the coefficient

  • vector. Hence, we have the following estimator:

δGMM = ( ¯ X ′ZWZ ′ ¯ X)−1 ¯ X ′ZWZ ′ ¯ Y , (5)

17 / 25

slide-18
SLIDE 18

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Results

Estimation Results

Variable Estimate SD Tweets 5.35∗∗∗ 0.36 T2Ratio 75, 653.54∗∗∗ 18,229.72 IntRatio 154, 698.00∗∗∗ 38,300.25 PosRatio 116, 681∗ 61,798.56 NegRatio −136, 926.9∗ 70445.52 Lag Revenue 0.30∗∗∗ 0.01 Ad 155.1425 203.7851

  • No. Weekly Observations:

433

Tweets Total number of tweets mentioning movie i in a week T2Ratio Ratio of type 2 tweets in a week IntRatio (%) Ratio of intention tweets in a week PosRatio (%) Ratio of tweets with positive sentiment in a week NegRatio (%) Ratio of tweets with negative sentiment in a week

18 / 25

slide-19
SLIDE 19

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? Results

Managerial Implications

Firms interested in the online WOM about their products should actively monitor or even seek WOM messages produced by people with large indegree in the social network. Companies may carefully monitor people’s intention toward certain products on Twitter and incorporate that information to better forecast future sales. The dual effect of intention tweets revealed in our study suggests the possibility of targeted advertising on Twitter.

19 / 25

slide-20
SLIDE 20

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

TwitterSensor

Individually, each tweet might be inconsequential and“boring” ; Collectively, the Twitterverse might reveal interesting patterns.

20 / 25

slide-21
SLIDE 21

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

TwitterSensor

21 / 25

slide-22
SLIDE 22

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

TwitterSensor

Figure 2:

22 / 25

slide-23
SLIDE 23

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

TwitterSensor

Figure 3:

23 / 25

slide-24
SLIDE 24

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

References

Avnit, A. 2009. The Million Followers Fallacy, Internet Draft, Pravda Media. http: // pravdam. com/ 2009/ 08/ 20/ the-million-followers-fallacy-guest-post-by-adi-avnit/ . Berinato, S. 2010. On Twitter, Followers Don’t Equal Influence. http://blogs.hbr.org/research/2010/05/influence-and-twitter.html Cha, M., H. Haddadi, F. Benevenuto, and K.P.Gummadi. 2010. Measuring User Influence in Twitter: The Million Follower Fallacy. Proc. International AAAI Conference on Weblogs and Social Media. Chevalier, J., and D. Mayzlin. 2006. The Effect of Word of Mouth on Sales: Online Book Reviews. Journal of Marketing Research, 43(3), 345-354. Chintagunta, P. K., S. Gopinath, and S. Venkataraman. The Effect of Online User Reviews on Movie Box Office Performance: Accounting for Sequential Rollout and Aggregation Across Local Markets. Marketing Science, forthcoming Dhar, V., and E. A. Chang. 2009. Does Chatter Matter? The Impact of User-Generated Content on Music Sales. Journal of Interactive Marketing, 23(4), 300-307. Duan, W., B. Gu, and A. B. Whinston. 2008. Do Online Reviews Matter? An Investigation of Panel Data. Decision Support Systems, 45(4), 1007-1016.

24 / 25

slide-25
SLIDE 25

Whose and What Chatter Matters? The Effect of Tweets on Movie Sales Whose and What Chatter Matters? TwitterSensor

References

Garber, M. 2010. Nicholas Christakis on the networked nature of Twitter. http://www.niemanlab.org/2010/12/ nicholas-christakis-on-the-networked-nature-of-twitter/ Godes, D., and D. Mayzlin. 2004. Using Online Conversations to Study Word-of-Mouth Communication. Marketing Science, 23(4), 545-560. Granovetter, M. 1973. The Strength of Weak Ties. The American Journal of Sociology, 78, 1360-1380. Olivera, F., P. Goodman, S. Tan. 2008. Contribution Behaviors in Distributed

  • Environments. MIS Quarterly, 32, 23-42.

Liu, Y. 2006. Word of Mouth for Movies: Its Dynamics and Impact on Box Office Revenue. Journal of Marketing, 70, 74-89. Onishi, H., and P. Manchanda. 2010. Marketing Activity, Blogging and Sales. Working paper. Sonnier, G. P., L. McAlister, and O. J. Rutz. 2011. A Dynamic Model of the Effect of Online Communications on Firm Sales. Marketing Science, 30(4), 702-716. Trusov, M., R. E. Bucklin, and K. Pauwels. 2009. Effects of Word-of-Mouth Versus Traditional Marketing: Findings from an Internet Social Networking Site. Journal of Marketing, 73, 90-102.

25 / 25