Filters








318 Hits in 4.8 sec

Developing Age and Gender Predictive Lexica over Social Media

Maarten Sap, Gregory Park, Johannes Eichstaedt, Margaret Kern, David Stillwell, Michal Kosinski, Lyle Ungar, Hansen Andrew Schwartz
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
The lexica, made publicly available, 1 achieved state-of-the-art accuracy in language based age and gender prediction over Facebook and Twitter, and were evaluated for generalization across social media  ...  We derive predictive lexica (words and weights) for age and gender using regression and classification models from word usage in Facebook, blog, and Twitter data with associated demographic labels.  ...  Acknowledgement Support for this work was provided by the Templeton Religion Trust and by Martin Seligman of the University of Pennsylvania's Positive Psychology Center.  ... 
doi:10.3115/v1/d14-1121 dblp:conf/emnlp/SapPEKSKUS14 fatcat:vjx5otmxg5anjhsmthag6ni4ey

Gender Prediction from Social Media Comments with Artificial Intelligence

Özer Çelik, Ahmet Faruk Aslan
2019 Sakarya University Journal of Science  
Also, with increasing use of social media, the companies have started to deliver their products and services to their customers via social media accounts.  ...  As a result of these ML developments, nowadays many companies use predictive models to estimate customer behavior.  ...  It was determined the lexica publicly available, was effective technique in language-based age and gender prediction over Facebook and Twitter.  ... 
doi:10.16984/saufenbilder.559452 fatcat:ipn77plj5bddrmiimef7sysh4i

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

Vivek Kulkarni, Margaret L. Kern, David Stillwell, Michal Kosinski, Sandra Matz, Lyle Ungar, Steven Skiena, H. Andrew Schwartz
2017 PLoS ONE   pre-print
The availability of social media data spanning millions of users now makes it possible to automatically derive characteristics from language use -- at large scale.  ...  Over the past century, personality theory and research has successfully identified core sets of characteristics that consistently describe and explain fundamental differences in the way people think, feel  ...  Predictive performance on social media based tasks for factors with residualization of age and gender.  ... 
doi:10.1371/journal.pone.0201703 pmid:30485276 pmcid:PMC6261386 arXiv:1705.08038v1 fatcat:pc4i626pbzbqhg3iwd3ytoulei

Extracting Human Temporal Orientation from Facebook Language

H. Andrew Schwartz, Gregory Park, Maarten Sap, Evan Weingarten, Johannes Eichstaedt, Margaret Kern, David Stillwell, Michal Kosinski, Jonah Berger, Martin Seligman, Lyle Ungar
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We quantify a users' overall temporal orientation based on their distribution of messages and validate it against known human correlates: conscientiousness, age, and gender.  ...  In this paper, we develop a novel behavior-based assessment using human language on Facebook.  ...  In this paper, we develop a temporal orientation measure based on language in social media.  ... 
doi:10.3115/v1/n15-1044 dblp:conf/naacl/SchwartzPSWEKSK15 fatcat:aqcs3zq435fpdjihwecom553qi

Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach

H. Andrew Schwartz, Johannes C. Eichstaedt, Margaret L. Kern, Lukasz Dziurzynski, Stephanie M. Ramones, Megha Agrawal, Achal Shah, Michal Kosinski, David Stillwell, Martin E. P. Seligman, Lyle H. Ungar, Tobias Preis
2013 PLoS ONE  
with personality, gender, and age.  ...  We analyzed 700 million words, phrases, and topic instances collected from the Facebook messages of 75,000 volunteers, who also took standard personality tests, and found striking variations in language  ...  Acknowledgments We would like to thank Greg Park, Angela Duckworth, Adam Croom, Molly Ireland, Paul Rozin, Eduardo Blanco, and our other colleagues in the Positive Psychology Center and Computer & Information  ... 
doi:10.1371/journal.pone.0073791 pmid:24086296 pmcid:PMC3783449 fatcat:eil6makofrd4lk6hvz6kzi7enq

Building Topic Models to Predict Author Attributes from Twitter Messages

Caitlin McCollister, Bo Luo, Shu Huang
2015 Conference and Labs of the Evaluation Forum  
These representations serve as inputs to a set of classifiers that make predictions for unknown authors' age, gender, extroversion, stability, agreeableness, conscientiousness, and openness.  ...  We also use MALLET to infer the most likely distribution over the generated topics that could have produced any given tweet instance, allowing us to represent tweets as concise 100-element document-topic  ...  For nominal attributes (age group and gender) we take the discrete class label that occurred most frequently in the individual predictions.  ... 
dblp:conf/clef/McCollisterLH15 fatcat:4m52vlj5abdwdelbiqlxctvncu

On the use of distributed semantics of tweet metadata for user age prediction

Abhinay Pandya, Mourad Oussalah, Paola Monachesi, Panos Kostakos
2019 Future generations computer systems  
Social media data represent an important resource for behavioral analysis of the aging population.  ...  To this end, we rely on language-related features and social media specific metadata.  ...  [22] constructed a predictive lexica from a dataset of Facebook users who agreed to share their status updates and reported their age and gender.  ... 
doi:10.1016/j.future.2019.08.018 fatcat:glstyfyt3vbk3ggrdtwo4gvdpu

Correcting Sociodemographic Selection Biases for Population Prediction from Social Media [article]

Salvatore Giorgi, Veronica Lynn, Keshav Gupta, Farhan Ahmed, Sandra Matz, Lyle Ungar, H. Andrew Schwartz
2022 arXiv   pre-print
Social media is increasingly used for large-scale population predictions, such as estimating community health statistics.  ...  However, social media users are not typically a representative sample of the intended population -- a "selection bias".  ...  Age and gender estimates were based on a demographic predictive lexica (Sap et al. 2014 ).  ... 
arXiv:1911.03855v4 fatcat:kaixdov77zelrblsfpwxc7swxa

DLATK: Differential Language Analysis ToolKit

H. Andrew Schwartz, Salvatore Giorgi, Maarten Sap, Patrick Crutchley, Lyle Ungar, Johannes Eichstaedt
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations  
pipelines for social-scientific prediction problems.  ...  We present Differential Language Analysis Toolkit (DLATK), an open-source python package and command-line tool developed for conducting social-scientific language analyses.  ...  DLATK is an open-source project out of the University of Pennsylvania and Stony Brook University.  ... 
doi:10.18653/v1/d17-2010 dblp:conf/emnlp/SchwartzGSCUE17 fatcat:364n7wjiurhv3l5xn4mtjyurd4

A Child's Garden of Curses: A Gender, Historical, and Age-Related Evaluation of the Taboo Lexicon

Jay, Jay
2013 American Journal of Psychology  
JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive.  ...  We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org. .  ...  and child swearing lexica over time.  ... 
doi:10.5406/amerjpsyc.126.4.0459 pmid:24455812 fatcat:x6ydnznic5f4rdcd5b754gdlze

World Trade Center responders in their own words: Predicting PTSD symptom trajectories with AI-based language analyses of interviews [article]

Youngseo Son, Sean A. P. Clouston, Roman Kotov, Johannes C. Eichstaedt, Evelyn J. Bromet, Benjamin J. Luft, H Andrew Schwartz
2020 arXiv   pre-print
Artificial Intelligence (AI) models promise to detect psychopathology in natural language, but they have been evaluated primarily in non-clinical settings using social media.  ...  Longitudinally, anxious language predicted future worsening in PCL scores (beta=0.31; p=0.031), whereas first-person plural usage (beta=-0.37; p=0.007) and longer words usage (beta=-0.36; p=0.007) predicted  ...  We also thank the clinical staff of the World Trade Center Medical Monitoring and Treatment Programs for their dedication and the labor and community organizations for their continued support.  ... 
arXiv:2011.06457v1 fatcat:64zwzeequ5cytocdkfcxtmtoqa

What demographic attributes do our digital footprints reveal? A systematic review

Joanne Hinds, Adam N. Joinson, David Garcia
2018 PLoS ONE  
Across these articles, 14 demographic attributes were successfully inferred from digital traces; the most studied included gender, age, location, and political orientation.  ...  method of prediction was automated, and (iii) the traces were either visible (e.g. tweets) or non-visible (e.g. clickstreams).  ...  Developing Age and Gender Predictive Lexica over Social Media.  ... 
doi:10.1371/journal.pone.0207112 pmid:30485305 pmcid:PMC6261568 fatcat:jo2ycsiit5a23drbbpytifn36q

Fusing Visual, Textual and Connectivity Clues for Studying Mental Health [article]

Amir Hossein Yazdavar, Mohammad Saeid Mahdavinejad, Goonmeet Bajaj, William Romine, Amirhassan Monadjemi, Krishnaprasad Thirunarayan, Amit Sheth, Jyotishman Pathak
2019 arXiv   pre-print
voluntarily and publicly on social media.  ...  With ubiquity of social media platforms, millions of people are sharing their online persona by expressing their thoughts, moods, emotions, feelings, and even their daily struggles with mental health issues  ...  layers, to predict gender and age from both the profile and shared images.  ... 
arXiv:1902.06843v1 fatcat:kskxnzqt6jdcli5pi6tpxrpnlq

World Trade Center responders in their own words: predicting PTSD symptom trajectories with AI-based language analyses of interviews

Youngseo Son, Sean A. P. Clouston, Roman Kotov, Johannes C. Eichstaedt, Evelyn J. Bromet, Benjamin J. Luft, H. Andrew Schwartz
2021 Psychological Medicine  
Artificial Intelligence (AI) models promise to detect psychopathology in natural language, but they have been evaluated primarily in non-clinical settings using social media.  ...  Longitudinally, anxious language predicted future worsening in PCL scores (β = 0.30; p = 0.049), whereas first-person plural usage (β = −0.36; p = 0.014) and longer words usage (β = −0.35; p = 0.014) predicted  ...  We also thank the clinical staff of the World Trade Center Medical Monitoring and Treatment Programs for their dedication and the labor and community organizations for their continued support.  ... 
doi:10.1017/s0033291721002294 pmid:34154682 pmcid:PMC8692489 fatcat:j47wxh4ubnbmxoslpyctvbngta

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

Veronica Lynn, Alissa Goodman, Kate Niederhoffer, Kate Loveys, Philip Resnik, H. Andrew Schwartz
2018 Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic  
Predictions of future psychological health can aid with both early detection and the development of preventative care.  ...  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.  ...  Acknowledgments We thank the UK ESRC for their support of essay transcriptions and initial analyses.  ... 
doi:10.18653/v1/w18-0604 dblp:conf/acl-clpsych/LynnGNLRS18 fatcat:msmvivyphrgotg72mczagml6xe
« Previous Showing results 1 — 15 out of 318 results