How do we measure evolving collaborative relationships, and their impact on systemic change? The National Science Foundation-funded Computing Alliance of Hispanic-Serving Institutions (CAHSI) Eddie Bernice Johnson INCLUDES community uses the collective impact framework to bring together stakeholders across sectors to tackle the problem of the underrepresentation of Hispanics in computing. This deep dive will share practical lessons learned to guide discussion with attendees who may be interested in developing mechanisms to measure social networks and the way they support change efforts.

Evaluating Collective Impact- Focusing on Social Networks for Developing Inclusive Excellence

Current theory suggests that the heterogeneity of metapopulation structure can help foster the diffusion of innovations to solve pressing issues including climate change adaptation and promoting public health. In this paper, we develop an agent-based model of the spread of adaptations in populations with such minority-majority metapopulation structure, where subpopulations have different preferences for social interactions (i.e., homophily) and, consequently, learn deferentially from their own group. In our simulations, minority-majority-structured populations with moderate degrees of in-group preference better spread and maintained an adaptation compared to populations with more equal-sized groups and weak homophily. Minority groups act as incubators for a novel adaptations, while majority groups act as reservoirs for the adaptation once it has spread widely. This suggests that population structure with in-group preference could promote the maintenance of novel adaptations, in the absence of out-group aversion.

Minority-group incubators and majority-group reservoirs for promoting the diffusion of climate change and public health adaptations

Much of our knowledge come from other people. In considering how argument quality and source reliability influences message persuasiveness, we conduct a comparison of the Elaboration Likelihood Model of Persuasion and the Bayesian Model of Argumentation, which are based on different assumptions. Participants were asked to judge a fictitious character’s degree of belief in a claim given evidence. To test competing predictions, we manipulate the character’s elaboration level, the argument’s quality, and the source’s reliability. The elaboration did not moderate the main effects of argument quality and source reliability, as they both were integral to the overall message strength in both high and low elaboration conditions. Bayesian predictions have better fit with the observed data, whilst ELM predictions did not align well. Overall, the BM is supported, but we discuss how this model could be further improvised while the ELM is contested


Comparing predictions from the Elaboration Likelihood Model and a Bayesian model of argumentation

Drawing on qualitative discourse analysis, this study conducted semi-structured interviews with seventeen sexual minorities, to investigate how the categorization mechanism generates institutional, interpersonal, and internalized stigmas and stressors against Chinese sexual minority youth, and how the categorization mechanism is represented in their contextualized lived experience. Heterosexual matrix and homonormativity hidden in Chinese traditions and ideologies are identified under the framework of queer linguistics. This study reveals that Chinese sexual minority youth are otherized as problematic out-groups on the textual level. They are negatively constructed as hypersexualized, pathologized, and dehumanized. On the micro-linguistic level, deixis, evaluations, and emotive words are used to classify in-groups and out-groups, show intimate and remote social distances, and express positive and negative attitudes. Results uncover that the categorization mechanism produces asymmetric relationships and power dynamics between heterosexual and non-heterosexual people, and between homonormative and non-homonormative sexual minorities.

The categorization mechanism in queer linguistics: A study on discourses of Chinese LGB youth

Petitions are a rich historical source, yet they have been relatively little used in historical research. In this paper, we aim to analyse Swedish texts from around the 18th century, and petitions in particular, using automatic means of text classification. We also test how text pre-processing and different feature representations affect the result, and we examine feature importance for our main class of interest - petitions. Our experiments show that the statistical algorithms NB, RF, SVM, and kNN are indeed very able to classify different genres of historical text. Further, we find that normalisation has a positive impact on classification, and that content words are particularly informative for the traditional models. A fine-tuned BERT model, fed with normalised data, outperforms all other classification experiments with a macro average F1 score at 98.8. However, using less computationally expensive methods, including feature representation with word2vec, fastText embeddings or even TF-IDF values, with a SVM classifier also show good results for both unnormalised and normalised data. In the feature importance analysis, where we obtain the features most decisive for the classification models, we find highly relevant characteristics of the petitions, namely words expressing signs of someone inferior addressing someone superior.


To the Most Gracious Highness, from Your Humble Servant: Analysing Swedish 18th Century Petitions Using Text Classification

Nowadays, the interest in code-mixing has become ubiquitous in Natural Language Processing (NLP); however, not much attention has been given to address this phenomenon for Speech Translation (ST) task. This can be solely attributed to the lack of code-mixed ST task labelled data. Thus, we introduce Prabhupadavani, which is a multilingual code-mixed ST dataset for 25 languages. It is multi-domain, covers ten language families, containing 94 hours of speech by 130+ speakers, manually aligned with corresponding text in the target language. The Prabhupadavani is about Vedic culture and heritage from Indic literature, where code-switching in the case of quotation from literature is important in the context of humanities teaching. To the best of our knowledge, Prabhupadvani is the first multi-lingual code-mixed ST dataset available in the ST literature. This data also can be used for a code-mixed machine translation task. All the dataset can be accessed at this https URL.

Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages

Generating a short story out of an image is arduous. Unlike image captioning, story generation from an image poses multiple challenges: preserving the story coherence, appropriately assessing the quality of the story,
steering the generated story into a certain
style, and addressing the scarcity of imagestory pair reference datasets limiting supervision during training. In this work, we introduce Plug-and-Play Story Teller (PPST) and
improve image-to-story generation by: 1) alleviating the data scarcity problem by incorporating large pre-trained models, namely CLIP
and GPT-2, to facilitate a fluent image-totext generation with minimal supervision, and
2) enabling a more style-relevant generation
by incorporating stylistic adapters to control
the story generation. We conduct image-tostory generation experiments with non-styled,
romance-styled, and action-styled PPST approaches and compare our generated stories
with those of previous work over three aspects, i.e., story coherence, image-story relevance, and style fitness, using both automatic
and human evaluation. The results show that
PPST improves story coherence and has better
image-story relevance, but has yet to be adequately stylistic.

Every picture tells a story: Image-grounded controllable stylistic story generation

In the news, statements from information sources are often quoted, made by individuals who interact in the news. Detecting those quotes and the gender of their sources is a key task when it comes to media analysis from a gender perspective. It is a challenging task: the structure of the quotes is variable, gender marks are not present in many languages, and quote authors are often omitted due to frequent use of coreferences. This paper proposes a strategy to measure the presence of women and men as information sources in news. We approach the problem of detecting sentences including quotes and the gender of the speaker as a joint task, by means of a supervised multiclass classifier of sentences. We have created the first datasets for Spanish and Basque by manually annotating quotes and the gender of the associated sources in news items. The results obtained show that BERT based approaches are significantly better than bag-of-words based classical ones, achieving accuracies close to 90%. We also analyse a bilingual learning strategy and generating additional training examples synthetically; both provide improvements up to 3.4% and 5.6\%, respectively.

 Measuring Presence of Women and Men as Information Sources in News

The task of computational textual narrative de- tection focuses on detecting the presence of narrative parts, or the degree of narrativity in texts. In this work, we focus on detecting the local degree of narrativity in texts, using short text passages. We performed a human annota- tion experiment on 325 English texts ranging across 20 genres to capture readers’ perception by means of three cognitive aspects: suspense, curiosity, and surprise. We then employed a linear regression model to predict narrativity scores for 17,372 texts. When comparing our average annotation scores to similar annotation experiments with different cognitive aspects, we found that Pearson’s r ranges from .63 to .75. When looking at the calculated narrative proba- bilities, Pearson’s r is .91. We found that it is possible to use suspense, curiosity and surprise to detect narrativity. However, there are still differences between methods. This does not imply that there are inherently correct methods, but rather suggests that the underlying defini- tion of narrativity is a determining factor for the results of the computational models employed.

Computational Detection of Narrativity: A Comparison Using Textual Features and Reader Response

In this paper, we explore the use of large language models to assess human interpretations of real world events. To do so, we use a language model trained prior to 2020 to artificially generate news articles concerning COVID-19 given the headlines of actual articles written during the pandemic. We then compare stylistic qualities of our artificially generated corpus with a news corpus, in this case 5,082 articles produced by CBC News between January 23 and May 5, 2020. We find our artificially generated articles exhibits a considerably more negative attitude towards COVID and a significantly lower reliance on geopolitical framing. Our methods and results hold importance for researchers seeking to simulate large scale cultural processes via recent breakthroughs in text generation.

The COVID That Wasn't: Counterfactual Journalism Using GPT

Wikipedia is widely used to train models for various tasks including semantic association, text generation, and translation. These tasks typically involve aligning and using text from multiple language editions, with the assumption that all versions of the article present the same content. But this assumption may not hold. We introduce a methodology for approximating the extent to which narratives of conflict may diverge in this scenario, focusing on articles about World War I and II battles written by Wikipedia's communities of editors across four language editions. For simplicity, our unit of analysis representing each language communities' perspectives is based on national entities and their subject-object-relation context, identified using named entity recognition and open-domain information extraction. Using a vector representation of these tuples, we evaluate how similarly different language editions portray how and how often these entities are mentioned in articles. Our results indicate that (1) language editions tend to reference associated countries more and (2) how much one language edition's depiction overlaps with all others varies.

War and Pieces: Comparing Perspectives About World War I and II Across Wikipedia Language Communities

Archive collections are nowadays mostly available through search engines interfaces, whichallow a user to retrieve documents by issuing
queries. The study of these collections may be, however, impaired by some aspects of search engines, such as the overwhelming number of
documents returned or the lack of contextual knowledge provided. New methods that could work independently or in combination with search engines are then required to access these collections. In this position paper, we propose to extend TimeLine Summarization (TLS) methods on archive collections to assist in their studies. We provide an overview of existing TLS methods and we describe a conceptual framework for an Archive TimeLine Summarization (ATLS) system, which aims to generate informative, readable and interpretable timelines.

Underline digital video library

Evaluating Collective Impact- Focusing on Social Networks for Developing Inclusive Excellence

Minority-group incubators and majority-group reservoirs for promoting the diffusion of climate change and public health adaptations

Comparing predictions from the Elaboration Likelihood Model and a Bayesian model of argumentation

The categorization mechanism in queer linguistics: A study on discourses of Chinese LGB youth

To the Most Gracious Highness, from Your Humble Servant: Analysing Swedish 18th Century Petitions Using Text Classification

Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages

Every picture tells a story: Image-grounded controllable stylistic story generation

Measuring Presence of Women and Men as Information Sources in News

Computational Detection of Narrativity: A Comparison Using Textual Features and Reader Response

The COVID That Wasn't: Counterfactual Journalism Using GPT

War and Pieces: Comparing Perspectives About World War I and II Across Wikipedia Language Communities

Archive TimeLine Summarization (ATLS): Conceptual Framework for Timeline Generation over Historical Document Collections

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES