290 likes | 556 Views
Understanding User Intents in Online Health Forums. Thomas Zhang, Jason H.D. Cho, Chengxiang Zhai Department of Computer Science University of Illinois at Urbana-Champaign 5 th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics Newport Beach, California
E N D
Understanding User Intents in Online Health Forums Thomas Zhang, Jason H.D. Cho, Chengxiang Zhai Department of Computer Science University of Illinois at Urbana-Champaign 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics Newport Beach, California 22nd September 2014
Online Health Forums • Purpose: To provide a convenient platform to facilitate discussion among patients and professionals • Hugeuser base, and still growing! • In 2011, 80% of all web users searched for health information online, of which 6% participated in health related discussions • Forums contain valuable information • Contain rich, often first hand experiences
Deficiencies of Forums • Threads are scattered • Similar questions are asked again and again • Keyword search is inadequate • Finding several keyword matches in a thread does not necessarily mean that the thread is relevant
Post about cholinergic urticaria in April 2004 Received 3rd and final reply a week later Post from March 2012 No replies as of July 2014
Applications of Intents • Improving thread retrieval • e.g. A thread whose original post matches both keywords and intent specified by the user are more likely to be helpful • Filtering threads • e.g. To treat a condition, only look at posts asking about treatment • Understanding user behavior in forums • i.e. users of different forums have different intents
This Paper • Introduces problem of identifying user intents in health forums as a classification problem • Derives the first taxonomy of user intents • Designs a set of novel features for use with machine learning to solve the problem • Create the first dataset for evaluation, and conducted experiments to make empirical findings
Roadmap • Problem formulation • Intent taxonomy derivation • Methodology • Support vector machines • Hierarchical classification • Feature design • Evaluation • Dataset • Experiments • Results • Intents in MedHelp forums • Wrap-up
Problem Formulation Given an original thread post from our dataset with intent from a taxonomy of user intents . Denote as the sentence representation of . Classify as some using as evidence. is correctly classified if and only if
Taxonomy Derivation • No taxonomy exists for health forum intents • Solution: Create our own! • First reduce top ten most commonly asked generic questions by doctors (Ely et al, 2000) into three intent classes • Classes match the intents of users who search for health information online (Choudhury et al, 2014) • Next introduce twoadditional intent classes that are specific to health forum posts
Taxonomy • Manage: How should I manage or treat condition X? • Cause: What is the cause of symptom/physical/test finding X? • Adverse: Can drug or treatment X cause adverse finding Y? • Combo: Combination (at least two of first three) • Story: Story telling, news, sharing or asking about experience, soliciting support, or others
Where are we? • Problem formulation • Intent taxonomy derivation • Methodology • Support vector machines • Feature Selection • Hierarchical classification • Evaluation • Dataset • Experiments • Results • Intents in MedHelp forums • Wrap-up
Support Vector Machines (SVM) • Main idea: Learn a hyperplanefrom examples to separate them into two classes • Use learned hyperplane to classify unseen examples • Capable of non-linear and multiclass classification • Shown to have good performance on high dimensional data
Post Representation • How should we representposts? • SVMs require examples to be represented as a vector of features • What are features? • Some measurable property of the observed data • How should we select them?
Feature Selection A good feature should be: • Genericenough to be found in many posts • Sufficientlydiscriminativefor different intents
Solution: Patterns! • Sequence of (possibly non-contiguous) tokens that represent recurring text patterns in sentences • Very generic • Lowercasing, stemming • POS tagging • UMLS semantic group tagging • Very discriminative • “What could X be…?” signifies Cause intent, but “What does X do…?” signifies Manageintent
Pattern Types Each pattern falls under one of fourtypes: • LSP: Lowercased + stemmed tokens only • E.g. “…what can caus…” • POSP: LSP + POS tags • E.g. “…how to <VERB>…” • SGP: LSP + semantic group tags • E.g. “…if <CHEM> works…” • ALL: All types of tokens and tags • E.g. “…<CHEM> make <PRP> feel…”
UMLS Semantic Groups • MetaMap labels text phrases with semantic group labels from the UMLS Metathesaurus
Caveat • Patterns possess limitations • Difficult to achieve good coverage without sacrificing discriminative properties • Impossible to extract for posts with large content variations (e.g. Story posts) • However, we still want completecoverage of our dataset!
Solution: Hierarchical Classification! Input Post • Two cascading SVM classifiers • The first uses binary pattern features (Pattern SVM) • The second uses unigram features with TF-IDF weighting (Word SVM) • Complete coverage allows comparison with unigram baseline Match ≥ 1 pattern? Yes No Word SVM Pattern SVM Output Class
Where are we? • Problem formulation • Intent taxonomy derivation • Methodology • Support vector machines • Hierarchical classification • Feature design • Evaluation • Dataset • Experiments • Results • Intents in MedHelp forums • Wrap-up
Dataset • No labeled dataset exists, since this is a new problem • So we create our own! • 1,192 original HealthBoards posts, evenly divided among four topics: allergies, breast cancer, depression, and heartdisease • Ideally want more posts, but labeling is expensive • Why the four topics?
Dataset Labeling • Labeling done by two CS students • Substantial*agreement with medical students () • Substantial*agreement between themselves (, labels match) • Combo posts labeled by a thirdCS student according to their underlying classes • A Combopost is predicted correctly if a classifier outputs one of its class labels *Per Landis and Koch, 1977
Experiments • What is the best performing set of patterns? • Try different typecombinations of patterns • How does hierarchical compare with baseline? • Five-fold cross validation (CV) • Does performance suffer if we train on posts from three topics and test on the fourth? • Four-fold forum CV
CV Takeaways • Patterns give high precision but low recall • Why is this acceptable? • Patterns generalize well across forum topics • Patterns reach labeling agreement upper bound • Overall improvement is underwhelming, why? Hierarchical Classification Performance Word Classifier (Baseline) Performance
Intents in MedHelp Forums We applied our Pattern SVM to 61,225 MedHelp posts split across allergies, breastcancer, depression, and heart disease
Concluding Remarks • Introduced the new problem of forum post intent analysis • Designed the first taxonomy and dataset for classification • Proposed a novel set of pattern features for SVMs • Proved that patterns give high classification precision while generalizing well across forums
Future Work • Administer study of health forum user intents • Expand pattern feature set to improve recall • Handle classification of Story posts • Identify all intents from Comboposts • Further evaluation with larger datasets
Thank you! Questions? Comments?