customer communication in twitter
TRANSCRIPT
Juniorprofessur fürKommunikations- undKollaborationsmanagement
Prof. Dr. Stefan Stieglitzwww.wi-kuk.de
KuKWIRTSCHAFTS INFORMATIK
Customer Communication in Twitter
A case study of Toyota in a crisis
Stefan StieglitzNina Krüger
Linh Dang-Xuan
DIATA ´11
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
2Customer Communication in Twitter
Agenda
Motivation and Background
Related Work
Research Design
Summary
Research Approach for the further study
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
3Customer Communication in Twitter
Social Media
Change in Public CommunicationOrganization (enterprise, political player, …)
Media (journalists as gatekeepers)Agenda Setting
Public Relations Public one-way communication
Customers, Citizens
Social Media marketing
Public Feedback, Questions, opinions, customer innovation
Communication between social media users• Complains• Trends etc.
Ideas, Innovations, opinions, Trends, complains, recommendations, etc…
Viral marketing, undercover actions
Media Monitoring
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
4Customer Communication in Twitter
What’s the difference?Opinion leaders are hard to identify
Much more data and richer information
Possibility to track data automatically and analyze them (digital information, ...) very fast (e.g. direct feedback on campaigns)
Everybody has a voice – risks and chances for companies
Long tail – opinion gathering
Choice of words – no strict rules like in press releases, different styles because of different platforms
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
5Customer Communication in Twitter
Research QuestionsGoals: getting a deeper understanding about the dynamics of the structures of
communication, the participation of the stakeholder and their sentiments in the communication.
1. Are crisis-related issues in twitter discussed (like in the classic media) and are these discussions characterized by peaks and buzzing-stages? Do involved user post higher frequented in peaks than in buzzing stages?
2. Are the postings in the peaks filled with more sentiment-words than in the buzzing stages?
3. Is there a difference between sentiments in Tweets created by power-tweeters (PT) only and the sentiments in Tweets created by all participants of the sample?
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
6Customer Communication in Twitter
Agenda
Motivation and Background
Related Work
Research Design
Summary
Research Approach for the further study
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
7Customer Communication in Twitter
Sentiment in Twitter Messages
Sentiment Analysis
• Sentiment analysis of Tweets: Events in the social, political, cultural and economic sphere do have a significant, immediate and highly specific effect on the various dimensions of public mood (Bollen et al., 2009).
• Link measures of public opinion derived from polls to sentiment measured from Twitter messages: Sentiment word frequencies in contemporaneous Twitter messages do correlate with several public opinion time series such as surveys on consumer confidence and political opinion over the 2008 to 2009 period (O’Connor et al., 2010).
• Study of political tweets around the 2009 German federal election: Tweet sentiment (e.g., positive and negative emotions associated with a politician) corresponds closely to voters’ political preferences (Tumasjan et al., 2010).
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
8Customer Communication in Twitter
Agenda
Motivation and Background
Related Work
Research Design
Summary
Research Approach for the further study
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
9Customer Communication in Twitter
ProceedingObjects of study: the Top10 players in the automotive industry
Identification of appropriate keywords using classic print media:•Identification of keywords by scanning the New York Times over a periode of two weeks,
analyzing these articles which are related to one of the carmakers.
Structural analysis of the course topics: •Observation, analysis and documentation of public communication in
Twitter using the keywords found with the help of a software prototype•Cleaning up the data
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
10Customer Communication in Twitter
Case selection
Identification of an issue•The large-scale car recall due to a technical fault in the gas pedals and the breaks
Using the keyword-combination „recall/-s“, „Toyota“
Implementation of the Issue Scanning for the periode 13-31 calendarweek:•732.003 Tweets: „Toyota“•37.232 Tweets: „recall“ und „Toyota“
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
11Customer Communication in Twitter
Outline data
5.870 Tweets with Hashtags (1.896 #toyota, 851 #recall) (16%)
3.190 Tweets with linked URLs (8,6%)
Relatively uniform distribution of users involved in the communication•The 10 most active Twitter accounts did 6.237 postings all in all (17,5 % of all Tweets)•Most active account: 1.237 Tweets (Toyota_recall)•The two identified official Toyota-account published only 237 and 164 Tweets
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
12Customer Communication in Twitter
Findings
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
13Customer Communication in Twitter
Sentiment Analysis
• Classifying the polarity of a given text at the document, sentence, or feature/aspect level
• Linguistic dimensions- Positive emotions (positive feelings, optimism)- Negative emotions (anger, anxiety, sadness)
• Example: Creating sentiment profile for companies, parties or affiliated individuals (e.g., in the form of positive/negative-emotion scales)
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
14Customer Communication in Twitter
Findings
Uniform percentage of sentiment words in the discussion
A clear tendency of a stronger polarization in peaks
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
15Customer Communication in Twitter
Account name Neutral Tweets Tweets with sentiment words
Toyota_recall 71,2 % 28,8 %
Toy_Yoda 79,5 % 20,5 %
toyotacomplaint 70,6 % 29,4 %
Toyotalinks 66,6 % 33,4 %
Toyotadispatch 69,2 % 30,8 %
Allairbagrecall 11,1 % 88,9 %
Prius_Bat_Recon 20,5 % 79,5 %
JaniceChase 85,5 % 14,5 %
Kulchawheels 55,4 % 44,6 %
VehixCar 60,4 % 39,6 %
Findings
Is there a difference between sentiments in Tweets created by power-tweeters (PT) only and the sentiments in Tweets created by all participants of the sample?
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
16Customer Communication in Twitter
Agenda
Motivation and Background
Research Approaches
Related Work
Summary
Research Approach for the further study
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
17Customer Communication in Twitter
SummaryOrganization-related issues are discussed in Twitter
Using the issue scanning keywords can identify topics for tracking dynamics
In crisis situations, more individuals participate in the discussion (the contribution per user does not rise)
In peak periods, there are clear trends in the discussion to positive or negative sentiments
Measures may differ in different types of discussion
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
18
Agenda
Motivation and Background
Related Work
Research Design
Summary
Research Approaches for the further study
Customer Communication in Twitter
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
19
Further Research
• Research on dynamics of specific topics in social networks
• Comparative studies of different cases
• Content analysis of the Tweets
• Social Network analysis
Customer Communication in Twitter
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
20Customer Communication in Twitter
Many thanks for your attention!
Juniorprofessur fürKommunikations- undKollaborationsmanagement(Prof. Dr. Stefan Stieglitz)Ku
K
WIRTSCHAFTS INFORMATIK
Universität MünsterInstitut für Wirtschaftsinformatik
Juniorprofessur für Kommunikations- undKollaborationsmanagement
Leonardo-Campus 3D-48149 Münster
http://www.wi.uni-muenster.de/kuk
Kontakt
2111.04.2023
Nina Krüger M.A.
[email protected] 83 38 014