UMBC Center for Social Science Scholarship

Permanent URI for this collectionhttp://hdl.handle.net/11603/19718

The Center for Social Science Scholarship promotes excellence across the social sciences at UMBC. Spanning disciplines and programs, we connect scholars who engage in social scientific study—asking key questions about social life, addressing problems of local and global concern, sharing knowledge about public issues, and connecting research to practice and policy.

Guided by the core principles of inclusion, equity, and diversity, we encourage intellectual exchange and cross-cutting dialogue as we strive to advance social progress and equity in ways that are critically relevant not only to UMBC but to our local, national, and global communities.

To foster high quality social science inquiry, we offer research and grant support, host trainings, promote campus and community events, and provide opportunities for academic as well as public debate, for the benefit of the university and society.

Browse

Now showing 1 - 20 of 73

Listening for Expert Identified Linguistic Features: Assessment of Audio Deepfake Discernment among Undergraduate Students
(2024-11-21) Bhalli, Noshaba Nasir; Naqvi, Nehal; Evered, Chloe; Mallinson, Christine; Janeja, Vandana
This paper evaluates the impact of training undergraduate students to improve their audio deepfake discernment ability by listening for expert-defined linguistic features. Such features have been shown to improve performance of AI algorithms; here, we ascertain whether this improvement in AI algorithms also translates to improvement of the perceptual awareness and discernment ability of listeners. With humans as the weakest link in any cybersecurity solution, we propose that listener discernment is a key factor for improving trustworthiness of audio content. In this study we determine whether training that familiarizes listeners with English language variation can improve their abilities to discern audio deepfakes. We focus on undergraduate students, as this demographic group is constantly exposed to social media and the potential for deception and misinformation online. To the best of our knowledge, our work is the first study to uniquely address English audio deepfake discernment through such techniques. Our research goes beyond informational training by introducing targeted linguistic cues to listeners as a deepfake discernment mechanism, via a training module. In a pre-/post- experimental design, we evaluated the impact of the training across 264 students as a representative cross section of all students at the University of Maryland, Baltimore County, and across experimental and control sections. Findings show that the experimental group showed a statistically significant decrease in their unsurety when evaluating audio clips and an improvement in their ability to correctly identify clips they were initially unsure about. While results are promising, future research will explore more robust and comprehensive trainings for greater impact.
Commentary: Bringing people and technology together to combat the threat of deepfakes
(Maryland Matters, 2024-03-25) Mallinson, Christine; Janeja, Vandana
UMBC team is creating and testing short training sessions to help listeners spot common 'tells' of real and fake speech.
ALDAS: Audio-Linguistic Data Augmentation for Spoofed Audio Detection
(2024-10-21) Khanjani, Zahra; Mallinson, Christine; Foulds, James; Janeja, Vandana
Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and phonological features of spoken English, manually annotated by experts, led to improved model performance. While this augmented model produced substantial improvements over traditional acoustic features based models, a scalability challenge motivates inquiry into auto labeling of features. In this paper we propose an AI framework, Audio-Linguistic Data Augmentation for Spoofed audio detection (ALDAS), for auto labeling linguistic features. ALDAS is trained on linguistic features selected and extracted by sociolinguistics experts; these auto labeled features are used to evaluate the quality of ALDAS predictions. Findings indicate that while the detection enhancement is not as substantial as when involving the pure ground truth linguistic features, there is improvement in performance while achieving auto labeling. Labels generated by ALDAS are also validated by the sociolinguistics experts.
Toward Transdisciplinary Approaches to Audio Deepfake Discernment
(2024-11-08) Janeja, Vandana; Mallinson, Christine
This perspective calls for scholars across disciplines to address the challenge of audio deepfake detection and discernment through an interdisciplinary lens across Artificial Intelligence methods and linguistics. With an avalanche of tools for the generation of realistic-sounding fake speech on one side, the detection of deepfakes is lagging on the other. Particularly hindering audio deepfake detection is the fact that current AI models lack a full understanding of the inherent variability of language and the complexities and uniqueness of human speech. We see the promising potential in recent transdisciplinary work that incorporates linguistic knowledge into AI approaches to provide pathways for expert-in-the-loop and to move beyond expert agnostic AI-based methods for more robust and comprehensive deepfake detection.
The Social Science of Activism and Storytelling w/ Dr. Tania Lizarazo
(UMBC Center for Social Science Research, 2024-08-20) Anson, Ian; Lizarazo, Tania
On today's episode I speak with Dr. Tania Lizarazo, Associate Professor in the Department of Modern Languages, Linguistics, and Intercultural Communication (MLLI) at UMBC. Dr. Lizarazo is also an affiliate faculty in the UMBC Global Studies program. Today's podcast discussion features mention of the following groups and projects:Mujeres Pacificas, a digital storytelling projectThe UMBC program in Critical Disability StudiesPostconflict Utopias (click the link to view the cover image, chosen by women from COCOMACIA!)Check out the following links for more information on UMBC, CS3, and our host:The UMBC Center for the Social Sciences ScholarshipThe University of Maryland, Baltimore CountyIan G. Anson, Ph.D.Retrieving the Social Sciences is a production of the UMBC Center for Social Science Scholarship. Our podcast host is Dr. Ian Anson, our director is Dr. Christine Mallinson, our associate director is Dr. Felipe Filomeno and our production intern is Jean Kim. Our theme music was composed and recorded by D’Juan Moreland. Special thanks to Amy Barnes and Myriam Ralston for production assistance. Make sure to follow us on Twitter, Facebook, Instagram, and YouTube, where you can find full video recordings of recent UMBC events.
The Social Science of Living Alone w/ Dr. Jun Chu
(UMBC Center for Social Science Research, 2024-09-26) Anson, Ian; Chu, Jun
On today's episode I speak with Dr. Jun Chu, Assistant Professor in the Department of Sociology, Anthropology, and Public Health at UMBC. Dr. Chu shares information about his ongoing research agenda into aging alone.Check out the following links for more information on UMBC, CS3, and our host:The UMBC Center for the Social Sciences ScholarshipThe University of Maryland, Baltimore CountyIan G. Anson, Ph.D.Retrieving the Social Sciences is a production of the UMBC Center for Social Science Scholarship. Our podcast host is Dr. Ian Anson, and our Acting director is Dr. Eric Stokan. Our production intern is Jean Kim. Our theme music was composed and recorded by D’Juan Moreland (UMBC '24). Special thanks to Amy Barnes and Myriam Ralston for production assistance. Make sure to follow us on Twitter, Facebook, Instagram, and YouTube, where you can find full video recordings of recent UMBC events.
Elections in Maryland w/ Jared DeMarinis
(UMBC Center for Social Science Research, 2024-10-15) DeMarinis, Jared; Anson, Ian
On today's episode we hear a rebroadcast of the 2024 UMBC Constitution Day Lecture, sponsored by UMBC's Center for Social Science Scholarship and the UMBC Department of Political Science. This year's lecture was delivered by Jared DeMarinis, the Maryland State Administrator of Elections. Mr. DeMarinis describes how elections work in Maryland, some of the state's early contributions to the way elections are conducted across the United States, and discusses the challenges of administering elections in a time of deep political polarization.Check out the following links for more information on UMBC, CS3, and our host:The UMBC Center for the Social Sciences ScholarshipThe University of Maryland, Baltimore CountyIan G. Anson, Ph.D.Retrieving the Social Sciences is a production of the UMBC Center for Social Science Scholarship. Our podcast host is Dr. Ian Anson, our director is Dr. Christine Mallinson, our associate director is Dr. Felipe Filomeno, and our production intern is Jean Kim. Our theme music was composed and recorded by D’Juan Moreland. Special thanks to Amy Barnes and Myriam Ralston for production assistance. Make sure to follow us on LinkedIn, Twitter, Facebook, Instagram, and YouTube, where you can find full video recordings of recent UMBC events.
ALDAS: Audio-Linguistic Data Augmentation for Spoofed Audio Detection
(2024-10-21) Khanjani, Zahra; Mallinson, Christine; Foulds, James; Janeja, Vandana
Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and phonological features of spoken English, manually annotated by experts, led to improved model performance. While this augmented model produced substantial improvements over traditional acoustic features based models, a scalability challenge motivates inquiry into auto labeling of features. In this paper we propose an AI framework, Audio-Linguistic Data Augmentation for Spoofed audio detection (ALDAS), for auto labeling linguistic features. ALDAS is trained on linguistic features selected and extracted by sociolinguistics experts; these auto labeled features are used to evaluate the quality of ALDAS predictions. Findings indicate that while the detection enhancement is not as substantial as when involving the pure ground truth linguistic features, there is improvement in performance while achieving auto labeling. Labels generated by ALDAS are also validated by the sociolinguistics experts.
Commentary: Bringing people and technology together to combat the threat of deepfakes
(Maryland Matters, 2024-03-25) Mallinson, Christine; Janeja, Vandana
UMBC team is creating and testing short training sessions to help listeners spot common 'tells' of real and fake speech.
Investigating Causal Cues: Strengthening Spoofed Audio Detection with Human-Discernible Linguistic Features
(2024-09-09) Khanjani, Zahra; Ale, Tolulope; Wang, Jianwu; Davis, Lavon; Mallinson, Christine; Janeja, Vandana
Several types of spoofed audio, such as mimicry, replay attacks, and deepfakes, have created societal challenges to information integrity. Recently, researchers have worked with sociolinguistics experts to label spoofed audio samples with Expert Defined Linguistic Features (EDLFs) that can be discerned by the human ear: pitch, pause, word-initial and word-final release bursts of consonant stops, audible intake or outtake of breath, and overall audio quality. It is established that there is an improvement in several deepfake detection algorithms when they augmented the traditional and common features of audio data with these EDLFs. In this paper, using a hybrid dataset comprised of multiple types of spoofed audio augmented with sociolinguistic annotations, we investigate causal discovery and inferences between the discernible linguistic features and the label in the audio clips, comparing the findings of the causal models with the expert ground truth validation labeling process. Our findings suggest that the causal models indicate the utility of incorporating linguistic features to help discern spoofed audio, as well as the overall need and opportunity to incorporate human knowledge into models and techniques for strengthening AI models. The causal discovery and inference can be used as a foundation of training humans to discern spoofed audio as well as automating EDLFs labeling for the purpose of performance improvement of the common AI-based spoofed audio detectors.
A place for (socio)linguistics in audio deepfake detection and discernment: Opportunities for convergence and interdisciplinary collaboration
(Wiley, 2024-07-09) Mallinson, Christine; Janeja, Vandana; Evered, Chloe; Khanjani, Zahra; Davis, Lavon; Bhalli, Noshaba Nasir; Nwosu, Kifekachukwu
Deepfakes, particularly audio deepfakes, have become pervasive and pose unique, ever-changing threats to society. This paper reviews the current research landscape on audio deepfakes. We assert that limitations of existing approaches to deepfake detection and discernment are areas where (socio)linguists can directly contribute to helping address the societal challenge of audio deepfakes. In particular, incorporating expert knowledge and developing techniques that everyday listeners can use to avoid deception are promising pathways for (socio)linguistics. Further opportunities exist for developing benevolent applications of this technology through generative AI methods as well.
Using Interdisciplinarity to Tackle Audio Deepfakes
(UMBC Center for Social Science Research, 2023-12-18) Anson, Ian; Nwosu, Kiffy; Evered, Chloe; Kim, Jean; Anson,Ian; Mallinson,Christine; Filomeno,Felipe; Kim,Jean; Moreland,D’Juan; Barnes,Amy; Ralston,Myriam; janeja,Vandana
On this episode, Dr. Anson speaks with two talented student researchers associated with the ongoing NSF-funded EAGER award led by Drs. Christine Mallinson and Vandana Janeja of UMBC. Kiffy Nwosu is an undergraduate computer science student from Maryland who has worked as a researcher at UMBC since high school, and is now a student at the Rochester Institute of Technology. Chloe Evered, originally of Houston, Texas, is a recent graduate of the Georgetown University department of linguistics with a minor in Chinese. Chloe is now pursuing a master’s degree in linguistics, also at Georgetown.
Predicting Hospitalization with the Hilltop Institute Analytics Research Team
(UMBC Center for Social Science Research, 2024-02-12) Anson, Ian; Goetschius, Leigh; Han, Fei; Henderson, Morgan; Kim, Jean; Anson,Ian; Mallinson,Christine; Filomeno,Felipe; Kim,Jean; Moreland,D’Juan; Barnes,Amy; Ralston,Myriam
On today’s episode we hear from Dr. Leigh Goetschius, Data Scientist Advanced, Dr. Fei Han, Principal Data Scientist and Affiliate Assistant Professor in the UMBC Department of Computer Science and Electrical Engineering, and Dr. Morgan Henderson, Principal Data Scientist and Affiliate Assistant Professor in the UMBC Department of Economics. Together, these researchers form the UMBC Hilltop Institute Analytics Research team. Our conversation focuses on their work in creating predictive models in the field of healthcare.
URCAD 2024
(UMBC Center for Social Science Research, 2024-05-01) Anson, Ian; Kim, Jean; Awan, Pakeeza; Joslow, Rachael; Hoang, Lien; Osei, Emmanuella; Cline, Carrington; Byrd, Ziegfried; Anson,Ian; Mallinson,Christine; Filomeno,Felipe; Kim,Jean; Moreland,D’Juan; Barnes,Amy; Ralston,Myriam
On today’s episode we hear about a series of fantastic presentations from UMBC’s Undergraduate Research and Creative Achievement Day, also known as URCAD. During URCAD, students from across the social science disciplines presented their excellent research to the campus community and beyond. Our special host for today’s episode is our production assistant, Jean Kim. Stay tuned for this wonderful celebration of undergraduate achievement–in podcasting as well as in social science research!
The Social Science of Reading for Pleasure with Dr. Tamara Bhalla and Jean Kim
(UMBC Center for Social Science Research, 2024-07-10) Anson, Ian; Bhalla, Tamara; Kim, Jean; Anson,Ian; Mallinson,Christine; Stokan,Eric; Kim,Jean; Moreland,D’Juan; Barnes,Amy; Ralston,Myriam
On this episode, Dr. Anson speaks with Dr. Tamara Bhalla, Associate Professor and Chair of the Department of American Studies at UMBC. Dr. Bhalla is also an affiliate faculty in the UMBC Asian Studies program. We also hear from Jean Kim, our very own podcast production assistant, about her role as a research assistant on Dr. Bhalla’s forthcoming book on the cultural context of reading.
Inclusion in Linguistics
(Oxford University Press, 2024-03-01) Hudley, Anne H. Charity; Mallinson, Christine; Bucholtz, Mary
Inclusion in Linguistics, the companion volume to Decolonizing Linguistics, aims to reinvent linguistics as a space of belonging across race, gender, class, disability, geographic region, and more. Taken together, the two volumes are the first comprehensive, action-oriented, book-length discussions of how to advance social justice in all aspects of the discipline. The volume's introduction theorizes inclusion as fundamental to social justice and describes the extensive dialogic and collaborative process through which the volume was developed. Contributors discuss intersectional forms of exclusion in linguistics: researchers' anti-autistic ableism; the exclusion of Deaf Global South researchers of color; the marginalization of Filipino American students and scholars; disciplinary transphobia; and the need for a “big tent” linguistics. The volume goes on to outline intersectional forms of exclusion in linguistics, describes institutional steps toward inclusion, offers examples of how to further educational justice, and shares models of collaborations designed to create an inclusive public-facing linguistics. The volume's conclusion outlines actions that linguists can take through research, teaching, and institutional structures to advance inclusion in linguistics and move the field toward social justice.
Decolonizing Linguistics
(Oxford University Press, 2024-03-01) Hudley, Anne H. Charity; Mallinson, Christine; Bucholtz, Mary
Decolonizing Linguistics, the companion volume to Inclusion in Linguistics, is designed to uncover and intervene in the history and ongoing legacy of colonization and colonial thinking in linguistics and related fields. Taken together, the two volumes are the first comprehensive, action-oriented, book-length discussions of how to advance social justice in all aspects of the discipline.The introduction to Decolonizing Linguistics theorizes decolonization as the process of centering Black, Native, and Indigenous perspectives, describes the extensive dialogic and collaborative process through which the volume was developed, and lays out key principles for decolonizing linguistic research and teaching. The twenty chapters cover a wide range of languages and linguistic contexts (e.g., Bantu languages, Creoles, Dominican Spanish, Francophone Africa, Zapotec) as well as various disciplines and subfields (applied linguistics, communication, historical linguistics, language documentation and revitalization/reclamation, psycholinguistics, sociolinguistics, syntax). Contributors address such topics as refusing settler-colonial practices and centering community goals in research on Indigenous languages; decolonizing research partnerships between the Global South and the Global North; and prioritizing Black Diasporic perspectives in linguistics. The volume's conclusion lays out specific actions that linguists can take through research, teaching, and institutional structures to refuse coloniality in linguistics and to move the field toward a decolonized future. , This is an open access title available under the terms of a CC BY-NC-ND 4.0 International license. It is free to read at Oxford Academic and offered as a free PDF download from OUP and selected open access locations. Decolonizing Linguistics, the companion volume to Inclusion in Linguistics, is designed to uncover and intervene in the history and ongoing legacy of colonization and colonial thinking in linguistics and related fields. Taken together, the two volumes are the first comprehensive, action-oriented, book-length discussions of how to advance social justice in all aspects of the discipline.The introduction to Decolonizing Linguistics theorizes decolonization as the process of centering Black, Native, and Indigenous perspectives, describes the extensive dialogic and collaborative process through which the volume was developed, and lays out key principles for decolonizing linguistic research and teaching. The twenty chapters cover a wide range of languages and linguistic contexts (e.g., Bantu languages, Creoles, Dominican Spanish, Francophone Africa, Zapotec) as well as various disciplines and subfields (applied linguistics, communication, historical linguistics, language documentation and revitalization/reclamation, psycholinguistics, sociolinguistics, syntax). Contributors address such topics as refusing settler-colonial practices and centering community goals in research on Indigenous languages; decolonizing research partnerships between the Global South and the Global North; and prioritizing Black Diasporic perspectives in linguistics. The volume's conclusion lays out specific actions that linguists can take through research, teaching, and institutional structures to refuse coloniality in linguistics and to move the field toward a decolonized future.
Community-Engaged Scholarship w/ Dr. Felipe Filomeno
(UMBC Center for Social Science Research, 2023-12-04) Anson, Ian; Filomeno, Felipe
On this special 50th episode, we hear from Dr. Felipe Filomeno, Associate Professor of Political Science and Associate Director of the Center for Social Science Scholarship (CS3) at UMBC. We discuss Dr. Filomeno’s approach to research through a discussion of community-engaged scholarship and his forthcoming book.
UMBC Social Science Alumni in Government, Business, and Non-Profit Careers
(UMBC Center for Social Science Research, 2023-11-13) Anson, Ian; Merner, Delta; Gibbons, Brent; Gay, Brittany; Filomeno, Felipe; Kim, Jean
On this episode we hear a rebroadcast of a special 5th anniversary event hosted by the UMBC Center for Social Science (CS3). The roundtable, which took place in October of 2023, brought together three fabulous UMBC alumni from across the social sciences: Dr. Delta Merner, (GES ’14), Lead Scientist, Science Hub for Climate Litigation at the Union of Concerned Scientists; Dr. Brent Gibbons, (PUBL ’13), Health Policy Researcher in the Health Economics Program at RTI International; and Dr. Brittany Gay, (PSYC ’21), Associate Director of Implementation Science at the Research-to-Policy Collaboration (RPC). The roundtable was moderated by CS3’s Associate Director, Dr. Felipe Filomeno. Click here for a full recording of the event.
”Kinlessness” and Aging w/ Dr. Christine Mair
(UMBC Center for Social Science Research, 2023-10-30) Anson, Ian; Mair, Christine A. ; Yamashita, Takashi
On this episode I speak with Dr. Christine Armstrong Mair, Associate Professor of Sociology and Gerontology and Director of the Center for Health, Equity, and Aging (CHEA) in the Department of Sociology, Anthropology, and Public Health (SAPH) at UMBC. We discuss Dr. Mair’s ongoing research into aging and older adult lifestyles across the world. Dr. Mair mentioned the following resources in our discussion: Gateway to Global Aging Data SMaRT Scholars Program National Academies of Science, Engineering, and Medicine (NASEM), Seminar on Kinlessness and Living Alone at Older Ages (Drs. Margolis, Carr, Taylor, and Mair)

Browse

Recent Submissions