Icwsm 2014 modeling user attitude v.7
-
Upload
jmahmud22 -
Category
Technology
-
view
230 -
download
1
Transcript of Icwsm 2014 modeling user attitude v.7
Modeling User Attitude toward Controversial Topics in Online Social Media
Huiji Gao*, Jalal Mahmud+, Jilin Chen+, Jeffrey Nichols+, Michelle Zhou+
*Arizona State University+IBM Research - Almaden
2014.06
1
2
Motivation
•400+ million tweets daily•3.2 billion Facebook likes
and comments daily
Hundreds of millions of people express themselves on social media daily Many social media campaigns emerged, where people express strong opinions and provide support for social causes of public interest Fracking Vaccination
Two users may hold the same negative sentiment toward a topic due to different opinions
However, they may take different actions due to their different opinions toward a topic
3
Motivating Example Joe may support the opinion that fracking causes damage to environment, believing that fracking should be immediately stopped.
Bill may believe that fracking harms environment, but is against the position of stopping fracking completely, believing that better regulation of fracking is needed.
Due to their different opinions, Joe and Bill may have different tendency to spread a petition that calls for stopping fracking, despite their shared negative sentiment.
Fracking Damages
Environment
Fracking Harms
EnvironmentCompletely
Agree
Not Completely
Agree
Spread Not Spread
4
Prior Work
Motivated by this gap, we present a unified computational model that captures people’s sentiment toward a topic, their specific
opinion, and their likelihood of taking an action.
Nuanced relationships between sentiment, opinion, and action has not been captured well by traditional sentiment or opinion analysis work (Jiang et al. 2011; Tan et al. 2011; Somasundaran and Wiebe 2010).
Prior behavior prediction work on social media (Yang et al. 2010; Feng and Wang 2013) are agnostic on the underlying opinions for behaviors, thus missing the potential effect of opinions in their prediction efforts.
Attitude Background
Tri-component Attitude Model Our model is inspired by an established theoretical framework in marketing research on attitudes and attitude models, where attitude is defined as a unified concept containing three aspects: “feelings”, “beliefs”, and “actions” (McGuire 1968; Schiffman and Kanuk 2010).
- According to the framework, beliefs are acquired on attitude object (e.g., a topic, product or person), which in turns influences the feelings on the object and the actions w.r.t. the attitude object.
Our computational model operationalizes this framework mathematically, casting feelings, beliefs, and actions into users’ sentiment, opinion, and action toward a topic on social media.
Attitude Example
Contributions
Study user attitude toward a controversial topic in terms of sentiment, opinion, and action.
Discover the relationships among sentiment, opinion and action, and model them for attitude prediction.
Perform experiments with real-world social media campaign datasets to demonstrate the model performance.
7
Methodology
Ground Truth Construction
Model Training
Attitude Prediction
- We consider re-tweeting an opinion about a topic as a ground truth and used supervised approach for labeling tweets.
- Model user action (e.g. re-tweeting) as preferences toward a target (e.g. a tweet)
- Adopt collaborative filtering method (e.g. matrix factorization) for action inference
- Introduce features (e.g. historical content, behavior, profile) in matrix factorization framework to handle “cold-start” users due to data sparsity.
- Bridge the gap between latent factors and explicit opinions expected as output.
- Introduce transition matrix to capture overall sentiment from opinions.
- Optimization for parameter Inference
- Predict Users’ Sentiment, Opinion and Action toward a topic.
9
User Attitude
Underlying Factors User Behavior
Problem: Model user behavior through his/her opinion/sentiment
Re-tweeting actions: Given a set of tweets, determine whether a user would re-tweet one or more tweets among them.
Inferring User Preferences towards a Set of Targets (Tweets)
Methodology
10
Methodology
Capturing User Retweeting Action with Matrix Factorization
R: User-tweet matrix representing re-tweeting actions
U: Low-rank representation of users’ latent preferences
V: Low-rank representation of tweets’ latent profiles
: Regularization terms
Inferring User Preferences towards a Set of Targets (Tweets)
Observed value in R is factorized into U and V;
An unknown user i’s preferences towards a tweet j, R(i,j), is approximated through Ui Vj
T
11
Methodology: Feature Selection for Preference Approximation
Inferring User Preferences towards a Target Capturing User Retweeting Action with Matrix Factorization
Introduce features in matrix factorization framework to handle “cold-start” users due to data sparsity.
User-related features
Feature coefficients
Sparse Feature Space
12
Methodology: Opinion Regularization Inferring User Preferences towards a Target
Capturing User Retweeting Action with Matrix Factorization
Bridge gaps between latent factors and explicit opinions:
A. Map user latent preferences into opinion space
B. Non-negativity Constraint for opinion interpretation
Observed user opinions
13
Methodology: Sentiment Regularization Inferring User Preferences towards a Target
Capturing User Retweeting Action with Matrix Factorization
Introduce transition matrix to capture overall sentiment from opinions
A. Introduce transition matrix S to map a user’s opinion preferences to sentiment polarity
B. Non-negativity constraint for sentiment interpretation
Opinion-sentiment transition matrix
Observed user sentiment polarity
14
ATMiner: Modeling User Attitude toward a Topic:
Action Factorization Opinion Regularization Sentiment Regularization
Sparse Learning
Avoid Over-fitting
Cold-Start Users
Non-negativity
Framework
Use Alternative non-negative least square to infer W, S, and V.
15
Modeling User Attitude
Input: R: User-Tweet Matrix; X: User-Feature Matrix;
O: User-Opinion Matrix; P: User-Sentiment Matrix.
User
Topic
Transition Matrix
Tweet Latent Profile
Features
RO
PS
V
X
FeatureCoefficients
W
Output: W: Feature Coefficients (Opinion Level);
S: Transition Matrix (Sentiment Level); V: Tweet Latent Profiles (Action Level).
Experiments
Tasks:1. Opinion Prediction:2. Sentiment Prediction:3. Retweeting Action Inference:
Experimental Setup – Data Collection
[1] D. Boyd, S. Golder, and G. Lotan. Tweet, tweet, retweet: Conversational aspects of retweeting on twitter. HICSS ’10, 2010.
[4] M. J. Welch, U. Schonfeld, D. He, and J. Cho. Topical semantics of twitter links. In Proc. of the WSDM ’11, 2011.
Selected fracking and vaccination as the controversial topics.
Used Twitter’s streaming API to obtain 1.6 million tweets related to fracking topic from Jan, 2013 to March, 2013, with a set of fracking-related keywords
For vaccination dataset, we obtained 1.1 million tweets related to vaccination topic from May, 2013 to Oct, 2013, with a set of vaccination-related keywords
Ranked all the crawled tweets based on their retweeted times, and selected those which are retweeted for more than 100 times as our action tweets.
There were 162 action tweets in fracking dataset and 105 action tweets in vaccination dataset.
Experimental Setup – Ground Truth Creation
Ground truth of action is available from the re-tweet of action tweets
Obtain corresponding users who re-tweeted action tweets, construct R - Following traditional assumption (Boyd, Golder, and Lotan 2010; Conover et al. 2011; Welch et al. 2011), re-tweeting is used as an endorsement of the original tweet.
Crawl users historical tweets, construct X
Manually label action tweets into eight opinion categories for fracking and six opinion categories for vaccination. - Instead of manually labeling each user in our dataset, we manually labeled only action tweets.
Assign user into opinion categories according to re-tweeting actions, construct O
Assign user into sentiment category according to opinion assignments, construct P - If the majority opinions assigned to this user are positive, the user is labeled as positive, otherwise negative.
Experimental Setup – OpinionsOpinions in the Fracking Dataset
18
Opinion Tweet Example
Fracking benefits economy and energy
Fracking saves us money; fracking creates jobs
Fracking is safe FACT: fracking has safely produced over 600 trillion cubic feet of #natgas since 1947.
Fracking causes oil spill Lives in a pineapple under the sea. BP oil spill.
Fracking damages environment
Large earthquake in Oklahoma in 2011 was caused by #fracking
Fracking causes health problems
To anyone speaking of the economic ”benefits” of fracking:what use is that money if your food and water are full of poison.
Fracking does not help economy
The amount of money BP lost from the oil spill could buy about 30 ice cream sandwiches for everyone on earth.
Fracking is bad Yoko Ono took a tour of gas drilling sites in PA to protest fracking.
Fracking should be stopped Protect our kids and families from #fracking. Please RT!
Experimental Setup - Opinions Opinions in the Vaccination Dataset
19
Opinion Tweet Example
Positive Information (Opinion)about vaccination
Vaccination campaign launches with hope of haltingmeasles outbreak http://t.co/H2B6ujFx22
Vaccination should be continued To not vaccinate is like manslaughter. Vaccinate!
Counter negative informationabout vaccination
Six vaccination myths - and why they’re wrong.http://t.co/BX7kq0SOjz
Negative Information (Opinion)about vaccination
Vaccination has never been proven to have saved onesingle life.
Vaccination causes disease Until the #Vaccination was introduced RT @trutherbot:Cancer was a rarity more than 200 years ago.
Criticize forced vaccination Police State? Registry System Being Set Up to TrackYour Vaccination Status - http://t.co/fkSWDbYAbB
Experimental SetupDatasets Statistics
20
User features based on users’ historical tweets. Use unigram model while removing stop-words to construct the feature space, and use term frequency as feature value. Cross validation, 70% for training and 30% for testing. All the parameters of our model are set through cross validation.
- Specifically, we set = 0.5, = 0.5, = 2, and = 0.1.
Fracking Vaccination
No. of Users 5,387 2,593
No. of Positive Users 1,562 1617
No. of Negative Users 3,822 976
Duration 1/13-3/13 5/13-10/13
No. of Historical Tweets 458,987 226,541
No. of Opinions 8 6
No. of Action Tweets 162 105
No. of Features 10,907 4,803
Experimental Results
Sentiment Prediction
21
Experimental Results
22
Opinion Prediction and Action Inference
Opinion Prediction-Fracking Opinion Prediction-Vaccination
Action Inference-Fracking Action Inference-Vaccination
Discussions
23
Conclusions
Presented a model to estimate a user’s attitude in terms of sentiment, opinion and likelihood of action toward controversial topics in social media.
Captured the relationships among sentiment, opinions and actions so as to predict actions and sentiment based on one’s opinions.
Our model extended traditional matrix factorization approach by usage of features, opinion and sentiment regularization.
Experiments using two real world datasets demonstrate that our model outperforms baselines in predicting sentiment, opinion and action.
24
25