Search Results - "Sap, Maarten"

Psychological Language on Twitter Predicts County-Level Heart Disease Mortality by Eichstaedt, Johannes C., Schwartz, Hansen Andrew, Kern, Margaret L., Park, Gregory, Labarthe, Darwin R., Merchant, Raina M., Jha, Sneha, Agrawal, Megha, Dziurzynski, Lukasz A., Sap, Maarten, Weeg, Christopher, Larson, Emily E., Ungar, Lyle H., Seligman, Martin E. P.

“…Hostility and chronic stress are known risk factors for heart disease, but they are costly to assess on a large scale. We used language expressed on Twitter to…”
Get full text

Empathy Toward Artificial Intelligence Versus Human Experiences and the Role of Transparency in Mental Health and Social Support Chatbot Design: Comparative Study by Shen, Jocelyn, DiPaola, Daniella, Ali, Safinah, Sap, Maarten, Park, Hae Won, Breazeal, Cynthia

“…Empathy is a driving force in our connection to others, our mental well-being, and resilience to challenges. With the rise of generative artificial…”
Get full text

Gaining Insights From Social Media Language: Methodologies and Challenges by Kern, Margaret L., Park, Gregory, Eichstaedt, Johannes C., Schwartz, H. Andrew, Sap, Maarten, Smith, Laura K., Ungar, Lyle H.

“…Language data available through social media provide opportunities to study people at an unprecedented scale. However, little guidance is available to…”
Get full text

Quantifying the narrative flow of imagined versus autobiographical stories by Sap, Maarten, Jafarpour, Anna, Choi, Yejin, Smith, Noah A, Pennebaker, James W, Horvitz, Eric

“…Lifelong experiences and learned knowledge lead to shared expectations about how common situations tend to unfold. Such knowledge of narrative event flow…”
Get full text

Positive AI with Social Commonsense Models by Sap, Maarten

“…To effectively understand language and safely communicate with humans, machines must not only grasp the surface meanings of texts, but also their underlying…”
Get full text

PREDICTING INDIVIDUAL WELL-BEING THROUGH THE LANGUAGE OF SOCIAL MEDIA by Schwartz, H Andrew, Sap, Maarten, Kern, Margaret L, Eichstaedt, Johannes C, Kapelner, Adam, Agrawal, Megha, Blanco, Eduardo, Dziurzynski, Lukasz, Park, Gregory, Stillwell, David, Kosinski, Michal, Seligman, Martin E P, Ungar, Lyle H

“…We present the task of predicting individual well-being, as measured by a life satisfaction scale, through the language people use on social media. Well-being,…”
Get more information

Living in the Past, Present, and Future: Measuring Temporal Orientation With Language by Park, Gregory, Schwartz, H. Andrew, Sap, Maarten, Kern, Margaret L., Weingarten, Evan, Eichstaedt, Johannes C., Berger, Jonah, Stillwell, David J., Kosinski, Michal, Ungar, Lyle H., Seligman, Martin E. P.

“…Temporal orientation refers to individual differences in the relative emphasis one places on the past, present, or future, and it is related to academic,…”
Get full text

Twitter sentiment predicts Affordable Care Act marketplace enrollment by Wong, Charlene A, Sap, Maarten, Schwartz, Andrew, Town, Robert, Baker, Tom, Ungar, Lyle, Merchant, Raina M

“…Traditional metrics of the impact of the Affordable Care Act (ACA) and health insurance marketplaces in the United States include public opinion polls and…”
Get full text

The 2013 US Government Shutdown (#Shutdown) and health: an emerging role for social media by Merchant, Raina M, Ha, Yoonhee P, Wong, Charlene A, Schwartz, H Andrew, Sap, Maarten, Ungar, Lyle H, Asch, David A

“…In October 2013, multiple United States (US) federal health departments and agencies posted on Twitter, "We're sorry, but we will not be tweeting or responding…”
Get full text

Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs by Yerukola, Akhila, Vaduguru, Saujas, Fried, Daniel, Sap, Maarten

“…Humans often express their communicative intents indirectly or non-literally, which requires their interlocutors -- human or AI -- to understand beyond the…”
Get full text

NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models by Rao, Abhinav, Yerukola, Akhila, Shah, Vishwa, Reinecke, Katharina, Sap, Maarten

“…To be effectively and safely deployed to global user populations, large language models (LLMs) must adapt outputs to user values and culture, not just know…”
Get full text

Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs by Zhou, Xuhui, Su, Zhe, Eisape, Tiwalayo, Kim, Hyunwoo, Sap, Maarten

“…Recent advances in large language models (LLM) have enabled richer social simulations, allowing for the study of various social phenomena. However, most recent…”
Get full text

Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty by Zhou, Kaitlyn, Hwang, Jena D, Ren, Xiang, Sap, Maarten

“…As natural language becomes the default interface for human-AI interaction, there is a need for LMs to appropriately communicate uncertainties in downstream…”
Get full text

Where Do People Tell Stories Online? Story Detection Across Online Communities by Antoniak, Maria, Mire, Joel, Sap, Maarten, Ash, Elliott, Piper, Andrew

“…Story detection in online communities is a challenging task as stories are scattered across communities and interwoven with non-storytelling spans within a…”
Get full text

From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models by Mendelsohn, Julia, Bras, Ronan Le, Choi, Yejin, Sap, Maarten

“…Dogwhistles are coded expressions that simultaneously convey one meaning to a broad audience and a second one, often hateful or provocative, to a narrow…”
Get full text

Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting by Yerukola, Akhila, Zhou, Xuhui, Clark, Elizabeth, Sap, Maarten

“…Most existing stylistic text rewriting methods and evaluation metrics operate on a sentence level, but ignoring the broader context of the text can lead to…”
Get full text

BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases by Zhang, Yiming, Nanduri, Sravani, Jiang, Liwei, Wu, Tongshuang, Sap, Maarten

“…Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and…”
Get full text

Towards Countering Essentialism through Social Bias Reasoning by Allaway, Emily, Taneja, Nina, Leslie, Sarah-Jane, Sap, Maarten

“…Essentialist beliefs (i.e., believing that members of the same group are fundamentally alike) play a central role in social stereotypes and can lead to harm…”
Get full text

Minion: A Technology Probe for Resolving Value Conflicts through Expert-Driven and User-Driven Strategies in AI Companion Applications by Fan, Xianzhe, Xiao, Qing, Zhou, Xuhui, Su, Yuran, Lu, Zhicong, Sap, Maarten, Shen, Hong

“…AI companions based on large language models can role-play and converse very naturally. When value conflicts arise between the AI companion and the user, it…”
Get full text

BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data by Li, Wenkai, Liu, Jiarui, Liu, Andy, Zhou, Xuhui, Diab, Mona, Sap, Maarten

“…In this work, we tackle the challenge of embedding realistic human personality traits into LLMs. Previous approaches have primarily focused on prompt-based…”
Get full text