Skip to search formSkip to main contentSkip to account menu

Hierarchical Modeling for User Personality Prediction: The Role of Message-Level Attention

A novel model is presented that uses message-level attention to learn the relative weight of users’ social media posts for assessing their five factor personality traits and yields state-of-the-art accuracies for all five traits.
View on ACL (opens in a new tab)

Human Centered NLP with User-Factor Adaptation

A continuous adaptation technique is introduced, suited for real-valued user factors that are common in social science and bringing us closer to personalized NLP, adapting to each user uniquely.
View on ACL (opens in a new tab)

CLPsych 2018 Shared Task: Predicting Current and Future Psychological Health from Childhood Essays

This shared task represents one of the first attempts to evaluate the use of early language to predict future health and has the potential to support a wide variety of clinical health care tasks, from early assessment of lifetime risk for mental health problems, to optimal timing for targeted interventions aimed at both prevention and treatment.
View on ACL (opens in a new tab)

Tweet Classification without the Tweet: An Empirical Examination of User versus Document Attributes

The predictive power of user-level features alone versus document- level features for document-level tasks is investigated, showing the performance of strong document-only models can often be improved with user attributes, particularly benefiting tasks with stable “trait-like” outcomes.
View on ACL (opens in a new tab)

Correcting Sociodemographic Selection Biases for Accurate Population Prediction from Social Media

Three methods to address predictive redistribution to account for shrinking, as well as adaptive binning and informed smoothing to handle sparse socio-demographic estimates are evaluated and it is shown each of these methods can significantly improve over the standard restratification approaches.

Correcting Sociodemographic Selection Biases for Population Prediction from Social Media

Three methods are developed and evaluated to address shrunken estimates (reduced variance of model predicted values) and sparse estimates of each population’s socio-demographic estimates: estimator redistribution to account for shrinking, adaptive binning and informed smoothing to handle sparse socio- Demographic estimates and combined approaches find substantial improvements over non-restratified models.
View on PubMed (opens in a new tab)

Residualized Factor Adaptation for Community Social Media Prediction Tasks

This paper presents residualized factor adaptation, a novel approach to community prediction tasks which both (a) effectively integrates community attributes, as well as (b) adapts linguistic features to community attributes (factors).
View on ACL (opens in a new tab)

Semantic Role Labeling for Process Recognition Questions

Empirical evaluation shows that manually generated roles provide a 12% relative improvement in accuracy over a simpler bag-of-words representation, but automatic role identification is noisy and doesn’t provide gains even with distant supervision and domain adaptation modifications to account for the limited training data.

POE: A Pathology Extraction Tool for Finding Attribute-Value Pairs in Glioma Pathology Reports

New integrative approaches that combine information from histologic, imaging and genomic features have the potential to advance methodologies for cancer classification and will likely necessitate development of new classification schemes.
View Paper (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)