Social Media Analytics

Transcription

1 Social Media Analytics 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 Engagement 2 1

2 Social Media Socialnomics video: 3 The Social Ecosystem Collaboration Analytics Engagement 4 Source: Forrester Research 2

3 SOCIAL MEDIA FOR COMMUNICATION AND COLLABORATION 5 Communication and Collaboration: Social Media Usage Source: McKinsey Quarterly

4 Communication and Collaboration: Benefits for Internal Use 7 Source: McKinsey Quarterly 2012 Communication and Collaboration: Alternative to ? French company Atos to ban internal usage. Statistics: 200 s per employee, per day 10% are useful 18% are spam Exploring other tools, including social media 8 Source: ABC News,

5 Communication and Collaboration: 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 5

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 Social Analytics Social Network Analysis Social Media Metrics Emotion Detection Social Media Monitoring Source: Gartner

7 Text Information Categories Multi-class problem Keyword-driven Series of binary or multi-class problems Multi-class problem Overlapping classes Multi-class problem Context dependent Topics Opinions Emotions Events Low Identification Complexity Complexities Linguistic features Literary devices (sarcasm, satire, rhetoric, irony, etc.) Spam Context High 13 Social Media Analytics: Opinion Mining Source: Chen

8 Social Media Analytics: Opinion Mining Source: Chen ONLINE SENTIMENTS AND FINANCIAL PERFORMANCE 16 8

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, Photo Books Now, free unlimited storage space 2/2008 Shutterfly Gallery 4/2009 iphone App Sources: Foresee, CNN Money, Internet Archives, 9

10 Online Customer Satisfaction Increased satisfaction score between 2009 and 2011 also resulted in increased stock price. 19 Social Media Sentiments as an Indicator? The strong relationship between stock price and sentiment polarity/intensity (sents) for Apple over a 24-hour period. Source: Das

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 86.7% accuracy in predicting closing up and down of DJIA using Twitter tweets Source: Bollen et al

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 billion/month in Sept billion/month in Mar billion/month in Jan billion/month in Apr billion/month in Jan

13 Social Media Analytics: Twitter Source: 25 USING SOCIAL MEDIA FOR DECISION-MAKING 26 13

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 Source: The Guardian

15 Social Media for M&A Analytics 29 Source: Lau et al Social Media for Early Warnings: ADRs 30 15

16 Social Media for Early Warnings: ADRs 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 Social Media for Early Warnings: ADRs Sentiments S(t) 0 Time t s Volume V(t) v 0 Time t Search Query U(t) u 0 FDA 0 Approval FDA 1 Black Box Change1 FDA 2 Black Box Change2 FDA 3 Withdrawal Time t 32 16

17 Social Media for Early Warnings: ADRs 33 Social Media for Early Warnings: ADRs 34 17

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 Social Media Analytics: Tiger Case Sentiment for Tiger Woods before and after scandal Combined from Twitter, blogs, forums, social networking sites, etc. 36 Source: Xenophon Strategies,

19 Social Media Analytics: Tiger Case Discussion keywords in Tiger conversations post scandal 4% - 7% of the postings mention a sponsor 37 Source: Xenophon Strategies, 2010 Social Media Analytics: Tiger Case Far greater reference to Tiger in Accenture conversations than Nike 38 Source: Xenophon Strategies,

20 Social Media Analytics: Tiger Case Sentiment for Accenture within Tiger Woods conversations 39 Source: Xenophon Strategies, 2010 Social Media Analytics: Tiger Case Sentiment for Accenture within Tiger Woods conversations after cutting ties with Tiger 40 Source: Xenophon Strategies,

21 Social Media Analytics: Tiger Case Sentiment for Nike within Tiger Woods conversations 41 Source: Xenophon Strategies, 2010 Social Media Analytics: Tiger Case 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 21

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 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 topic Sources: Akismet 2012; Websense 2010; Choi et al

23 Challenges: Spam Websites and Blogs 45 Source: Abbasi et al Challenges: Spam - Reviews 46 Sources: Ott et al

24 Challenges: Spam - Detection Spam Cues: Lengthier Higher average word length More descriptive and vivid 47 Sources: Ntoulas et al. 2006; Ott et al Challenges: Sentiment Accuracy Analyzed performance of several SaaS opinion 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 accuracy 48 24

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. Sources: Gartner Challenges: Context the why A Text Analytics Framework for Sense-making 50 25

26 Discussion: Tea bag manufacturer's dilemma Challenges: Context the why?, Manufacturers can develop new products. Try to develop new products. But I think that manufacturers must invest funds to do academic research. Then the development of new product has certain theory and factual basis. 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 to older man, slimming tea to young woman, and packaging milk tea. 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 dilemma Manufacturers can develop new products.,? Try to develop new products. But I think that manufacturers must invest funds to do academic research. Then the development of new product has certain theory and factual basis.? 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 to older man, slimming tea to young woman, and packaging milk tea. 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. Donation CANNOT promote the brand. 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? 51 SOCIAL MEDIA FOR CUSTOMER ENGAGEMENT 52 26

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

28 Online Social Media Usage 55 Source: One Up Web 2010 The Conversion Funnel: e-tailer 56 28

29 The Conversion Funnel: Social Media Source: Peter Chang, 57 SMR Study: How to get Retweeted 25% follow a brand 67% purchase from the brand they follow 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 Source: Malhotra et al

30 ? 59 30