1,720,980 research outputs found
The Geography of U.S. Companies That Care About Their Employees
No full textInvestment in employees is increasingly vital for fostering a sustainable and inclusive workplace. While past research has linked investment in employees (i.e., financial benefits and well-being efforts) to individual company performance, it mainly overlooked how these benefits relate to a broader state level. Our study gathered over 350,000 employee reviews of 104 major U.S. companies from 2008 to 2020, used deep learning to assess company investment in employees in these reviews, and associated these companies with the U.S. states in which they are located. Based on a state-level factor analysis, we discovered that there are two main facets that relate to investment in employees: one with primary focus on financial benefits; and a more comprehensive one that, in addition to financial, incorporates a set of other, more intangible benefits, such as as health, education, diversity, infrastructure and atmosphere. We then found that states hosting companies investing in the latter facet tended to be economically prosperous, and attractive to the "creative class."This fresh perspective on internal corporate efforts has significant implications for economic geography, workplaces, and the computational social science literature
How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
No full textAs NLP models are increasingly deployed in socially situated settings such as online abusive content detection, it is crucial to ensure that these models are robust. One way of improving model robustness is to generate counterfactually augmented data (CAD) for training models that can better learn to distinguish between core features and data artifacts. While models trained on this type of data have shown promising out-of-domain generalizability, it is still unclear what the sources of such improvements are. We investigate the benefits of CAD for social NLP models by focusing on three social computing constructs — sentiment, sexism, and hate speech. Assessing the performance of models trained with and without CAD across different types of datasets, we find that while models trained on CAD show lower in-domain performance, they generalize better out-of-domain. We unpack this apparent discrepancy using machine explanations and find that CAD reduces model reliance on spurious features. Leveraging a novel typology of CAD to analyze their relationship with model performance, we find that CAD which acts on the construct directly or a diverse set of CAD leads to higher performance
Visualizing Internal Sustainability Efforts in Big Companies
No full textInternal sustainability efforts (ISE) refer to a wide range of internal corporate policies focused on employees. They promote, for example, work-life balance, gender equality, and a harassment-free working environment. At times, however, companies fail to keep their promises by not publicizing truthful reports on these practices, or by overlooking employees voices on how these practices are implemented. To partly fix that, we developed a deep-learning framework that scored four fifths of the S&P 500 companies in terms of six ISEs, and a web-based system that engages users in a learning and reflection process about these ISEs. We evaluated the system in two crowdsourced studies with 421 participants, and compared our treemap visualization with a baseline textual representation. We found that our interactive treemap increased by up to 7% our participants opinion change about ISEs, demonstrating its potential in machine-learning driven visualization
The unseen targets of hate: a systematic review of hateful communication datasets
Full text linkMachine learning (ML)-based content moderation tools are essential to keep online spaces free from hateful communication. Yet ML tools can only be as capable as the quality of the data they are trained on allows them. While there is increasing evidence that they underperform in detecting hateful communications directed towards specific identities and may discriminate against them, we know surprisingly little about the provenance of such bias. To fill this gap, we present a systematic review of the datasets for the automated detection of hateful communication introduced over the past decade, and unpack the quality of the datasets in terms of the identities that they embody: those of the targets of hateful communication that the data curators focused on, as well as those unintentionally included in the datasets. We find, overall, a skewed representation of selected target identities and mismatches between the targets that research conceptualizes and ultimately includes in datasets. Yet, by contextualizing these findings in the language and location of origin of the datasets, we highlight a positive trend towards the broadening and diversification of this research space
The Unseen Targets of Hate: A Systematic Review of Hateful Communication Datasets
No full textMachine learning (ML)-based content moderation tools are essential to keep online spaces free from hateful communication. Yet ML tools can only be as capable as the quality of the data they are trained on allows them. While there is increasing evidence that they underperform in detecting hateful communications directed towards specific identities and may discriminate against them, we know surprisingly little about the provenance of such bias. To fill this gap, we present a systematic review of the datasets for the automated detection of hateful communication introduced over the past decade, and unpack the quality of the datasets in terms of the identities that they embody: those of the targets of hateful communication that the data curators focused on, as well as those unintentionally included in the datasets. We find, overall, a skewed representation of selected target identities and mismatches between the targets that research conceptualizes and ultimately includes in datasets. Yet, by contextualizing these findings in the language and location of origin of the datasets, we highlight a positive trend towards the broadening and diversification of this research space
Insider Stories: Analyzing Internal Sustainability Efforts of Major US Companies from Online Reviews
Full text linkIt is hard to establish whether a company supports internal sustainability
efforts (ISEs) like gender equality, diversity, and general staff welfare, not
least because of lack of methodologies operationalizing these internal
sustainability practices, and of data honestly documenting such efforts. We
developed and validated a six-dimension framework reflecting Internal
Sustainability Efforts (ISEs), gathered more than 350K employee reviews of 104
major companies across the whole US for the (2008-2020) years, and developed a
deep-learning framework scoring these reviews in terms of the six ISEs.
Commitment to ISEs manifested itself at micro-level -- companies scoring high
in ISEs enjoyed high stock growth. This new conceptualization of ISEs offers
both theoretical implications for the literature in corporate sustainability,
and practical implications for companies and policymakers. To further explore
these implications, researchers need to add potentially missing ISEs, to do so
for more companies, and establish the causal relationship between company
success and ISEs.Comment: 9 pages + 15 pages of appendix, to appear in Humanities & Social
Sciences Communication
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
