Social Media Sentiment Analysis
-
Upload
burak-akguen -
Category
Education
-
view
237 -
download
16
Transcript of Social Media Sentiment Analysis
Social Media LandscapeMEHMET BURAK AKGÜN
AwarenessDo enough people know about us? Do enough people think about us?
ContextDo people think of us in the right way?
ValueDo people understand our value? What we offer?
RelevanceDo people appreciate our value to them?
CatalystsDo people have a reason to think about us? To engage with us? To buy into us?
Brand Momentum Drivers
Social Media coulddrive, amplify and reinforce all of these things
2
Sales: Net New Customers, Increased Frequency of Transactions, promo exposure. Increased yield (average $ value per transaction), and product penetration
Customer Support: Immediate feedback and response, positive impact in public forum, cost reduction
Human Resources: More effective recruiting, online monitoring of employee behavior (risk management)
Public Relations: Online Reputation Management, improved brand image via Social Web
Customer Loyalty: Increased interactions, better quality of interactions, deeper relationship with brand. Increased trust in brand, increased mindshare of brand, greater values alignment
Business Intelligence: Know Everything.
Ways Social Media Can Help Business
3
4
user-generated media• Importance of opinions:
– Opinions are important because whenever we need to make a decision, we want to hear others’ opinions.
– In the past, • Individuals: opinions from friends and family• businesses: surveys, focus groups, consultants …
• Word-of-mouth on the Web– User-generated media: One can express opinions on anything in
reviews, forums, discussion groups, blogs ...
– Opinions of global scale: No longer limited to:• Individuals: one’s circle of friends• Businesses: Small scale surveys, tiny focus groups, etc.
An Example Review• “I bought an iPhone a few days ago. It was such a nice
phone. The touch screen was really cool. The voice quality was clear too. Although the battery life was not long, that is ok for me. However, my mother was mad with me as I did not tell her before I bought the phone. She also thought the phone was too expensive, and wanted me to return it to the shop. …”
• What do we see?– Opinions, targets of opinions, and opinion holders
5
Can we successfully predict the sentiment of an Instagram hashtag?
6
Instagram Overview
• Instagram – Photo sharing social network
• Each post can contain a caption and hashtags
• Hashtags group posts into categories
• Express extra information/emotion about the post
7
Hashtag Overview
• Composed of words, phrases, and acronyms• Often contain misspellings, made up words, and
slang/vernacular
#love#myfriendsarehotterthanyourfriends
#likeabos#ugly
#depresstion#selfharmmm
8
% of Twitter Members Using Twitter to:
9
Text Data: Twitter
• A large and public social media service– Good: Has people writing their thoughts– Bad: News, celebrities, “media” stuff (?)
• Sources1.Archiving the Twitter Streaming API
“Gardenhose”/”Sample”: ~10-15% of public tweets
2.Scrape of earlier messagesthanks to Brendan Meeder, CMU
• ~2 billion messages before topic selection,Jan 2008 – May 2010
10
Message data{ "text": "Time for the States to fight back !!! Tenth Amendment Movement: Taking On the Feds http://bit.ly/14t1RV #tcot #teaparty”, "created_at": "Tue Nov 17 21:08:39 +0000 2009", "geo": null, "id": 5806348114, "in_reply_to_screen_name": null, "in_reply_to_status_id": null, "user": { "screen_name": "TPO_News", "created_at": "Fri May 15 04:16:38 +0000 2009", "description": "Child of God - Married - Gun carrying NRA Conservative - Right Winger hard Core Anti Obama (Pro America), Parrothead - www.ABoldStepBack.com #tcot #nra #iPhone", "followers_count": 10470, "friends_count": 11328, "name": "Tom O'Halloran", "profile_background_color": "f2f5f5", "profile_image_url": "http://a3.twimg.com/profile_images/295981637/TPO_Balcony_normal.jpg", "protected": false, "statuses_count": 21147, "location": "Las Vegas, Baby!!", "time_zone": "Pacific Time (US & Canada)", "url": "http://www.tpo.net/1dollar", "utc_offset": -28800, }}
11
Message data we use{ "text": "Time for the States to fight back !!! Tenth Amendment Movement: Taking On the Feds http://bit.ly/14t1RV #tcot #teaparty”, "created_at": "Tue Nov 17 21:08:39 +0000 2009”}
1. Text2. Timestamp
• Message data we do not use:– Locations from GPS– Locations from IP addresses – not public– User information (name, description, self-described location)– Conversation structure: retweets, replies– Social structure: follower network
12
Survey Data
• Consumer confidence, 2008-2009– Index of Consumer Sentiment (Reuters/Michigan)– Gallup Daily (free version from gallup.com)
• 2008 Presidential Elections– Aggregation, Pollster.com
• 2009 Presidential Job Approval– Gallup Daily
• Which tweets correspond to these polls?
13
Message selection via topic keywords
• Analyzed subsets of messages that contained manually selected topic keyword– “economy”, “jobs”, “job”– “obama”– “obama”, “mccain”
• High day-to-day volatility– Fraction of messages containing keyword– Nov 5 2008: 15% of tweets contain “obama”
14
Sentiment analysis: word counting
• Subjectivity Clues lexicon from OpinionFinder (Univ. of Pittsburgh)– Wilson et al 2005– 2000 positive, 3600 negative words
• Procedure1.Within topical messages,2.Count messages containing these positive and
negative words
15
Sentiment Ratio over Messages
For one day t and a particular topic word, compute score
SentimentRatio( topic_word, t ) =
16
8% YoY Growth
Establish A Baseline
17
What are people talking about and where? Map topics, keywords, trends, links, etc.
Monitor Impact On Conversations
18