AWARE-TEXT: An Android Package for Mobile Phone Based Text Collection and On-Device Processing | VIDEO

How we perceive our surrounding world impacts how we live in and react to it. In this study, we propose LaBel (Latent Beliefs Model), an alternative to topic modeling that uncovers latent semantic dimensions from transformer-based embeddings and enables their representation as generated phrases rather than word lists. We use LaBel to explore the major beliefs that humans have about the world and other prevalent domains, such as education or parenting. Although human beliefs have been explored in previous works, our proposed model helps automate the exploring process to rely less on human experts, saving time and manual efforts, especially when working with large corpus data. Our approach to LaBel uses a novel modification of autoregressive transformers to effectively generate texts conditioning on a vector input format. Differently from topic modeling methods, our generated texts (e.g. “the world is truly in your favor”) are discourse segments rather than word lists, which helps convey semantics in a more natural manner with full context. We evaluate LaBel dimensions using both an intrusion task as well as a classification task of identifying categories of major beliefs in tweets finding greater accuracies than popular topic modeling approaches.

Modeling Latent Dimensions of Human Beliefs

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". Within the social sciences, such a bias is typically addressed with restratification techniques, where observations are reweighted according to how under- or over-sampled their socio-demographic groups are. Yet, restratifaction is rarely evaluated for improving prediction.  Across four tasks of predicting U.S. county population health statistics from Twitter, we find standard restratification techniques provide no improvement and often degrade prediction accuracies. The core reasons for this seems to be both shrunken estimates (reduced variance of model predicted values) and sparse estimates of each population's socio-demographics. We thus develop and evaluate three methods to address these problems: estimator redistribution to account for shrinking, and adaptive binning and informed smoothing to handle sparse socio-demographic estimates. We show that each of these methods significantly outperforms the standard restratification approaches. Combining approaches, we find substantial improvements over non-restratified models, yielding a 53.0% increase in predictive accuracy (R^2) in the case of surveyed life satisfaction, and a 17.8% average increase across all tasks.

Correcting Sociodemographic Selection Biases for Population Prediction from Social Media

The word embedding association test (WEAT) is an important method for measuring linguistic biases against social groups such as ethnic minorities in large text corpora. It does so by comparing the semantic relatedness of words prototypical of the groups (e.g., names unique to those groups) and attribute words (e.g., ‘pleasant’ and ‘unpleasant’ words). We show that anti-black WEAT estimates from geo-tagged social media data at the level of metropolitan statistical areas strongly correlate with several measures of racial animus—even when controlling for sociodemographic covariates. However, we also show that every one of these correlations is explained by a third variable: the frequency of Black names in the underlying corpora relative to White names. This occurs because word embeddings tend to group positive (negative) words and frequent (rare) words together in the estimated semantic space. As the frequency of Black names on social media is strongly correlated with Black Americans’ prevalence in the population, this results in spurious anti-Black WEAT estimates wherever few Black Americans live. This suggests that research using the WEAT to measure bias should consider term frequency, and also demonstrates the potential consequences of using black-box models like word embeddings to study human cognition and behavior.

Negative Associations in Word Embeddings Predict anti-Black Bias Across Regions--but only via Name Frequency

Black Lives Matter (BLM) is a decentralized social movement protesting violence against Black individuals and communities, with a focus on police brutality. The movement gained significant attention following the killings of Ahmaud Arbery, Breonna Taylor, and George Floyd in 2020. The #BlackLivesMatter social media hashtag has come to represent the grassroots movement, with similar hashtags counter protesting the BLM movement, such as #AllLivesMatter, and #BlueLivesMatter. We introduce a data set of 63.9 million tweets from 13.0 million users from over 100 countries which contain one of the following keywords: BlackLivesMatter, AllLivesMatter, and BlueLivesMatter.  This data set contains all currently available tweets from the beginning of the BLM movement in 2013 to 2021. We summarize the data set and show temporal trends in use of both the BlackLivesMatter keyword and keywords associated with counter movements.  Additionally, for each keyword, we create and release a set of Latent Dirichlet Allocation (LDA) topics (i.e., automatically clustered groups of semantically co-occuring words) to aid researchers in identifying linguistic patterns across the three keywords.

Twitter Corpus of the #BlackLivesMatter Movement And Counter Protests: 2013 to 2021

**Workshop Organizers:** Geeticka Chauhan, Dmitrijs Milajevs, Elijah Rippeth, Jeremy Gwinnup and Liling Tan
 *Coffee Break 10:30 am* 
*Lunch Break 12:30 pm* 
*Coffee Break 3:30 pm* [**Workshop Website**](https://nlposs.github.io/2023/index.html) br>With great scientific breakthrough comes solid engineering and open communities. The Natural Language Processing (NLP) community has benefited greatly from the open culture in sharing knowledge, data, and software. The primary objective of this workshop is to further the sharing of insights on the engineering and community aspects of creating, developing, and maintaining NLP open source software (OSS), which we seldom talk about in scientific publications. Our secondary goal is to promote synergies between different open source projects and encourage cross-software collaborations and comparisons. [**Invited Speakers**](https://nlposs.github.io/2023/index.html#invited-speakers)
 [**Go to Gather**](https://app.gather.town/app/ROH1myZvp9ba7a3C/EMNLP2023?spawnToken=NkRDtAxGTAO66WTylwFf)

W07: The 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS)

workshop paper

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

s3-3: Modeling human behavior

technical paper

**ICWSM-2022 will be held from June 6th – 9th in a hybrid format, both in-person in Atlanta, Georgia and online.**

**The Workshop and Tutorial Sessions are accessible to those that registered separately for these sessions. If you registered to attend but are not able to access the these sessions from the [Schedule tab](https://underline.io/events/291/schedule?day=2022-06-06T04%3A00%3A00.000Z), please email icwsm@underline.io
**

The International AAAI Conference on Web and Social Media (ICWSM) is a forum for researchers from multiple disciplines to come together to share knowledge, discuss ideas, exchange information, and learn about cutting-edge research in diverse fields with the common theme of online social media. This overall theme includes research in new perspectives in social theories, as well as computational algorithms for analyzing social media. ICWSM is a singularly fitting venue for research that blends social science and computational approaches to answer important and challenging questions about human social behavior through social media while advancing computational tools for vast and unstructured data.


ICWSM, now in its sixteenth year, has become one of the premier venues for computational social science, and previous years of ICWSM have featured papers, posters, and demos that draw upon network science, machine learning, computational linguistics, sociology, communication, and political science. The uniqueness of the venue and the quality of submissions have contributed to a rapidly growing conference, and a competitive acceptance rate of approximately 20% for full-length research papers published in the proceedings by the Association for the Advancement of Artificial Intelligence (AAAI).


**ICWSM Code of Conduct**

All persons, organizations and entities that attend AAAI conferences and events are subject to the standards of conduct set forth on the [AAAI Code of Conduct for Events and Conferences](https://aaai.org/Conferences/code-of-conduct.php). AAAI expects all community members to formally endorse this code of conduct, and to actively prevent and discourage any undesired behaviors. Everyone should feel empowered to politely engage when they or others are disrespected, and to raise awareness and understanding of this code of conduct. AAAI event participants asked to stop their unacceptable behavior are expected to comply immediately. Sponsors are also subject to this code of conduct in their participation in AAAI events.


Additionally, participants are encouraged to be courteous when sharing screen captures and photographs of conference events. Seek permission when possible and respect requests to take down images if those featured ask. Concerns around code of conduct or inclusion may be sent to icwsm22@aaai.org. If you have any concerns or items to report, please reach out to the General Chairs: Diyi Yang and Yelena Mejova.

A ticket is required to attend the event, please use the below URL to register for the event if you have not already done so:

https://aaaiconf.cventevents.com/event/be8c26b0-a76f-4753-babb-de2bd9d2a619/summary

Virtual-Only:
$200 AAAI Member
$125 AAAI Student Member
$225 Nonmember
$150 Nonmember Student

Virtual Silver: Includes discounted conference registration, plus a one-year online new or renewed membership in AAAI.
$299 Silver Regular
$174 Silver Student

Virtual - Workshop and Tutorials:
$45 Regular
$25 Student


Registration Is Required

ICWSM 2022

The International AAAI Conference on Web and Social Media (ICWSM) is a forum for researchers from multiple disciplines to come together to share knowledge, discuss ideas, exchange information, and learn about cutting-edge research in diverse fields with the common theme of online social media. This overall theme includes research in new perspectives in social theories, as well as computational algorithms for analyzing social media. ICWSM is a singularly fitting venue for research that blends social science and computational approaches to answer important and challenging questions about human social behavior through social media while advancing computational tools for vast and unstructured data.

Salvatore Giorgi

5

1

SHORT BIO

Presentations

AWARE-TEXT: An Android Package for Mobile Phone Based Text Collection and On-Device Processing | VIDEO

Modeling Latent Dimensions of Human Beliefs

Correcting Sociodemographic Selection Biases for Population Prediction from Social Media

Negative Associations in Word Embeddings Predict anti-Black Bias Across Regions--but only via Name Frequency

Twitter Corpus of the #BlackLivesMatter Movement And Counter Protests: 2013 to 2021

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES