Search Results for author: H. Andrew Schwartz

Found 45 papers, 10 papers with code

Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation

no code implementations1 Jun 2023 Adithya V Ganesan, Yash Kumar Lal, August Håkan Nilsson, H. Andrew Schwartz

Very large language models (LLMs) perform extremely well on a spectrum of NLP tasks in a zero-shot setting.

Psychological Metrics for Dialog System Evaluation

no code implementations24 May 2023 Salvatore Giorgi, Shreya Havaldar, Farhan Ahmed, Zuhaib Akhtar, Shalaka Vaidya, Gary Pan, Lyle H. Ungar, H. Andrew Schwartz, Joao Sedoc

We present metrics for evaluating dialog systems through a psychologically-grounded "human" lens in which conversational agents express a diversity of both states (e. g., emotion) and traits (e. g., personality), just as people do.

Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge

1 code implementation3 May 2023 Vasudha Varadarajan, Swanie Juhng, Syeda Mahwish, Xiaoran Liu, Jonah Luby, Christian Luhmann, H. Andrew Schwartz

While transformer-based systems have enabled greater accuracies with fewer training examples, data acquisition obstacles still persist for rare-class tasks -- when the class label is very infrequent (e. g. < 5% of samples).

Active Learning Implicit Discourse Relation Classification +1

Human Language Modeling

1 code implementation Findings (ACL) 2022 Nikita Soni, Matthew Matero, Niranjan Balasubramanian, H. Andrew Schwartz

Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently.

Age Estimation Language Modelling +3

MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection

1 code implementation Findings (EMNLP) 2021 Matthew Matero, Nikita Soni, Niranjan Balasubramanian, H. Andrew Schwartz

Much of natural language processing is focused on leveraging large capacity language models, typically trained over single messages with a task of predicting one or more tokens.

Language Modelling Masked Language Modeling +1

Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality

1 code implementation NAACL 2021 Adithya V Ganesan, Matthew Matero, Aravind Reddy Ravula, Huy Vu, H. Andrew Schwartz

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models, limiting the ability to effectively leverage transformers.

Dimensionality Reduction

Autoregressive Affective Language Forecasting: A Self-Supervised Task

1 code implementation COLING 2020 Matthew Matero, H. Andrew Schwartz

Human natural language is mentioned at a specific point in time while human emotions change over time.

Detecting Emerging Symptoms of COVID-19 using Context-based Twitter Embeddings

1 code implementation EMNLP (NLP-COVID19) 2020 Roshan Santosh, H. Andrew Schwartz, Johannes C. Eichstaedt, Lyle H. Ungar, Sharath C. Guntuku

In this paper, we present an iterative graph-based approach for the detection of symptoms of COVID-19, the pathology of which seems to be evolving.

Quantifying Community Characteristics of Maternal Mortality Using Social Media

1 code implementation14 Apr 2020 Rediet Abebe, Salvatore Giorgi, Anna Tedijanto, Anneke Buffone, H. Andrew Schwartz

While most mortality rates have decreased in the US, maternal mortality has increased and is among the highest of any OECD nation.

Correcting Sociodemographic Selection Biases for Population Prediction from Social Media

1 code implementation10 Nov 2019 Salvatore Giorgi, Veronica Lynn, Keshav Gupta, Farhan Ahmed, Sandra Matz, Lyle Ungar, H. Andrew Schwartz

However, social media users are not typically a representative sample of the intended population -- a "selection bias".

Selection bias

Suicide Risk Assessment with Multi-level Dual-Context Language and BERT

no code implementations WS 2019 Matthew Matero, Akash Idnani, Youngseo Son, Salvatore Giorgi, Huy Vu, Mohammad Zamani, Parth Limbachiya, Sharath Ch Guntuku, ra, H. Andrew Schwartz

Mental health predictive systems typically model language as if from a single context (e. g. Twitter posts, status updates, or forum posts) and often limited to a single level of analysis (e. g. either the message-level or user-level).

Identifying Locus of Control in Social Media Language

no code implementations EMNLP 2018 Masoud Rouhizadeh, Kokil Jaidka, Laura Smith, H. Andrew Schwartz, Anneke Buffone, Lyle Ungar

Individuals express their locus of control, or {``}control{''}, in their language when they identify whether or not they are in control of their circumstances.

Causal Explanation Analysis on Social Media

no code implementations EMNLP 2018 Youngseo Son, Nipun Bayas, H. Andrew Schwartz

Understanding causal explanations - reasons given for happenings in one's life - has been found to be an important psychological factor linked to physical and mental health.

Discourse Parsing

Residualized Factor Adaptation for Community Social Media Prediction Tasks

no code implementations EMNLP 2018 Mohammadzaman Zamani, H. Andrew Schwartz, Veronica E. Lynn, Salvatore Giorgi, Niranjan Balasubramanian

Predictive models over social media language have shown promise in capturing community outcomes, but approaches thus far largely neglect the socio-demographic context (e. g. age, education rates, race) of the community from which the language originates.

Predicting Human Trustfulness from Facebook Language

no code implementations WS 2018 Mohammadzaman Zamani, Anneke Buffone, H. Andrew Schwartz

Trustfulness -- one's general tendency to have confidence in unknown people or situations -- predicts many important real-world outcomes such as mental health and likelihood to cooperate with others such as clinicians.

Using Search Queries to Understand Health Information Needs in Africa

no code implementations14 Jun 2018 Rediet Abebe, Shawndra Hill, Jennifer Wortman Vaughan, Peter M. Small, H. Andrew Schwartz

The lack of comprehensive, high-quality health data in developing nations creates a roadblock for combating the impacts of disease.


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

no code implementations WS 2018 Veronica Lynn, Alissa Goodman, Kate Niederhoffer, Kate Loveys, Philip Resnik, H. Andrew Schwartz

We describe the shared task for the CLPsych 2018 workshop, which focused on predicting current and future psychological health from an essay authored in childhood.

Domain Adaptation from User-level Facebook Models to County-level Twitter Predictions

no code implementations IJCNLP 2017 Daniel Rieman, Kokil Jaidka, H. Andrew Schwartz, Lyle Ungar

Several studies have demonstrated how language models of user attributes, such as personality, can be built by using the Facebook language of social media users in conjunction with their responses to psychology questionnaires.

Domain Adaptation

Human Centered NLP with User-Factor Adaptation

no code implementations EMNLP 2017 Veronica Lynn, Youngseo Son, Vivek Kulkarni, Niranjan Balasubramanian, H. Andrew Schwartz

We pose the general task of user-factor adaptation {--} adapting supervised learning models to real-valued user factors inferred from a background of their language, reflecting the idea that a piece of text should be understood within the context of the user that wrote it.

Document Classification Domain Adaptation +4

DLATK: Differential Language Analysis ToolKit

no code implementations EMNLP 2017 H. Andrew Schwartz, Salvatore Giorgi, Maarten Sap, Patrick Crutchley, Lyle Ungar, Johannes Eichstaedt

We present Differential Language Analysis Toolkit (DLATK), an open-source python package and command-line tool developed for conducting social-scientific language analyses.

General Classification

Assessing Objective Recommendation Quality through Political Forecasting

no code implementations EMNLP 2017 H. Andrew Schwartz, Masoud Rouhizadeh, Michael Bishop, Philip Tetlock, Barbara Mellers, Lyle Ungar

Recommendations are often rated for their subjective quality, but few researchers have studied comment quality in terms of objective utility.

Sentiment Analysis

Latent Human Traits in the Language of Social Media: An Open-Vocabulary Approach

no code implementations22 May 2017 Vivek Kulkarni, Margaret L. Kern, David Stillwell, Michal Kosinski, Sandra Matz, Lyle Ungar, Steven Skiena, H. Andrew Schwartz

Taking advantage of linguistic information available through Facebook, we study the process of inferring a new set of potential human traits based on unprompted language use.

Using Twitter Language to Predict the Real Estate Market

no code implementations EACL 2017 Mohammadzaman Zamani, H. Andrew Schwartz

We explore whether social media can provide a window into community real estate -foreclosure rates and price changes- beyond that of traditional economic and demographic variables.


Cannot find the paper you are looking for? You can Submit a new open access paper.