Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Astrophysics (172)
- Cosmology and astronomy (79)
- Galaxies (63)
- Mobile computing (59)
- Security (52)
-
- Stars (52)
- Quantum physics (47)
- Wireless (46)
- Mhealth (38)
- Network (38)
- Humans (33)
- Privacy (33)
- Supernova remnants (32)
- Supernovae (30)
- Condensed matter (29)
- Cosmology (28)
- Physics (28)
- Models (27)
- Parallel computing (27)
- File system (26)
- Ubicomp (25)
- Classical and quantum mechanics (24)
- Distributed computing (24)
- General physics (24)
- Sensors (23)
- High energy physics (22)
- Mass (22)
- Quasars (22)
- Methods (21)
- Parallel-io (21)
- Publication Year
- Publication
-
- Dartmouth Scholarship (1104)
- Computer Science Technical Reports (372)
- Dartmouth College Undergraduate Theses (227)
- Dartmouth College Ph.D Dissertations (112)
- Dartmouth College Master’s Theses (62)
-
- Computer Science Senior Theses (25)
- Dartmouth Undergraduate Journal of Science (10)
- Chemistry 52, Gordon Gribble lectures on Special Topics (9)
- ENGS 88 Honors Thesis (AB Students) (7)
- Environmental Studies Senior Theses (6)
- Other Faculty Materials (3)
- Other Staff Materials (2)
- Cognitive Science Senior Theses (1)
- Geography Undergraduate Senior Theses (1)
- Independent Student Projects and Publications (1)
- Quantitative Social Science Undergraduate Senior Theses (1)
- Wetterhahn Science Symposium Posters 2018 (1)
- Publication Type
- File Type
Articles 1 - 30 of 1944
Full-Text Articles in Entire DC Network
The Impact Of Maine’S Municipal Shellfish Management On Clam Harvester Motivation To Participate In Resource Conservation, Rachel Lohr Freer
The Impact Of Maine’S Municipal Shellfish Management On Clam Harvester Motivation To Participate In Resource Conservation, Rachel Lohr Freer
Environmental Studies Senior Theses
This study investigates how the resource management strategies implemented by Maine’s different Municipal Shellfish Conservation Committees influences the motivation held by shellfish harvesters’ to participate in resource conservation activities. As soft shell clam landings are declining across Maine due to increasing predation and climate-related stress, there seems to be a disconnect in harvesters’ willingness to support the conservation activities that Shellfish Conservation Committees make available to them. In efforts to improve participation, town leadership in select regions have started to mandate the completion of annual conservation hours requirements. The diversity of policy approaches enacted by towns provides the unique opportunity …
Conserving The Public Lands: Policy And Spatial Analysis Of A Bureau Of Land Management Conservation Leasing Mechanism, Isaiah M. Menning
Conserving The Public Lands: Policy And Spatial Analysis Of A Bureau Of Land Management Conservation Leasing Mechanism, Isaiah M. Menning
Environmental Studies Senior Theses
The Bureau of Land Management (BLM) is the largest land administrator in the United States, managing about 10% of U.S. lands, primarily in the Western states. The BLM manages under a multiple-use framework, issuing commercial authorizations for grazing, mining, oil and gas, and wind and solar on public lands, while also managing for ecosystem health. In April 2024, the agency finalized a rule that would create a conservation leasing mechanism to allow private, state, and tribal parties to lease BLM lands for restoration and mitigation purposes, which I investigate here. First, I find that while the conservation leasing mechanism does …
Land-Use Governance And Indigenous Engagement In Arctic Alaska And Norway: Successes, Current Gaps, And Paths Forward, Ningning Sun
Land-Use Governance And Indigenous Engagement In Arctic Alaska And Norway: Successes, Current Gaps, And Paths Forward, Ningning Sun
Environmental Studies Senior Theses
This study aims to analyze the land use governance structures and the role of Indigenous engagement in Alaska and Norway using a comparative approach, with special focus on successful practices, current gaps, and paths forward to achieve equitable governance. Extractive land uses, such as oil and gas extraction and the construction of wind farms, have mixed impacts on Indigenous communities and lead to social and legal issues such as land use conflict and environmental injustice. Previous research has studied land use governance in Arctic countries with regard to Indigenous Peoples, yet there is a lack of literature that spans Alaska …
Fiscal Incentives For Green Growth: A Mixed-Methods Study Of The State Of Agroforestry And Tree Cover In India, Spriha Pandey
Fiscal Incentives For Green Growth: A Mixed-Methods Study Of The State Of Agroforestry And Tree Cover In India, Spriha Pandey
Environmental Studies Senior Theses
Agroforestry is a crucial strategy for diversifying farmer livelihoods and achieving India's climate goals, but its adoption has been hindered by institutional and fiscal obstacles. This mixed-methods study investigates the impact of national government schemes on tree cover increase and expert perceptions of incentives and barriers to agroforestry adoption. Our analysis of national schemes from 2013-2017 reveals that effective fiscal mechanisms and policy cohesion are critical drivers of agroforestry growth. Specifically, we find that increased funding for the Rural Employment Guarantee Scheme (MGNREGS) is associated with significant increases in tree cover area while funding for the Horticultural Scheme (NHM) is …
An Economic Remodel: The Genesis Of Modern Corporate Sustainability, Caitlin R. Doak
An Economic Remodel: The Genesis Of Modern Corporate Sustainability, Caitlin R. Doak
Environmental Studies Senior Theses
My thesis aims to understand and analyze what is catalyzing the advancement of sustainability in corporate agendas. After my internship at Deloitte and four years of Dartmouth undergrad, I recognized some important themes emerging in the sustainability landscape. Sustainability is at the forefront of policy and stakeholder engagement right now. Shareholders, consumers, regulators, policy makers, are all putting pressure on CSuite executives to redefine materiality and increase transparency in order to properly understand sustainability-related risks and opportunities within companies. Climate and nature-related disclosures are becoming just as important as financial disclosures because companies are being evaluated holistically, and a company’s …
The Dartmouth Land Ethic: Synthesizing Environmental Ethical Beliefs In Hanover And Beyond, Conor M. Roemer
The Dartmouth Land Ethic: Synthesizing Environmental Ethical Beliefs In Hanover And Beyond, Conor M. Roemer
Environmental Studies Senior Theses
In this thesis, I seek to explore the nature of an environmental ethical paradigm at Dartmouth. In order to do so, I have chosen to begin with an examination of Aldo Leopold’s Land Ethic. This watershed essay has inspired many environmental ethical inquiries in the last eighty years. Leopold’s Land Ethic urged human beings to view the environment beyond what might be extracted for anthropogenic use and to see the land as a summation of everything that lies within it: not just the plants and animals, but the mountains, rocks, rivers, and soil as well. In turn, scores of philosophers …
On Adaptivity And Randomness For Streaming Algorithms, Manuel Stoeckl
On Adaptivity And Randomness For Streaming Algorithms, Manuel Stoeckl
Dartmouth College Ph.D Dissertations
A streaming algorithm has a limited amount of memory and reads a long sequence (data stream) of input elements, one by one, and computes an output depending on the input. Such algorithms may be used in an online fashion, producing a sequence of intermediate outputs corresponding to the prefixes of the data stream. Adversarially robust streaming algorithms are required to give correct outputs with a desired probability even when the data stream is adaptively generated by an adversary that can see all intermediate outputs of the algorithm. This thesis binds together research on a variety of problems related to the …
Probing Central Spin Decoherence Dynamics Of Electronic Point Defects In Diamond And Silicon, Ethan Que Williams
Probing Central Spin Decoherence Dynamics Of Electronic Point Defects In Diamond And Silicon, Ethan Que Williams
Dartmouth College Ph.D Dissertations
Electron spins of point defects in diamond and silicon can exhibit long coherence times, making them attractive platforms for the physical implementation of qubits for quantum sensing and quantum computing. To realize these technologies, it is essential to understand the mechanisms that limit their coherence. Decoherence of these systems is well described by the central spin model, wherein the central electron spin weakly interacts with numerous electron and nuclear spins in its environment. The dynamics of the resultant dephasing can be probed with pulse electron paramagnetic resonance (pEPR) experiments.
Using a 2.5 GHz pEPR spectrometer built in-house, we performed multi-pulse …
The Shifting Landscape Of Adolescent Wellness In Boarding Schools: Can Time Spent Off Screens And Outdoors Improve Adolescent Wellbeing?, Kristen H. Peterson
The Shifting Landscape Of Adolescent Wellness In Boarding Schools: Can Time Spent Off Screens And Outdoors Improve Adolescent Wellbeing?, Kristen H. Peterson
Dartmouth College Master’s Theses
For nearly twenty years I have worked directly with adolescents as an independent school educator. Whether in the classroom, on the field, or in the dorm, I have observed and supported students through their middle and high school experiences. During this time, I have witnessed an alarming shift in adolescent physical, emotional, and social wellbeing. Concurrently, I have observed a dramatic increase in the amount of time students spend using screen-based devices, and a decrease in their time spent outdoors.
Using research to ground my anecdotal accounts in empirical understanding, my thesis examines whether or not screen use might help …
Poster, Performed: Understanding Public Opinions Of Authorship In Generative Artificial Intelligence Models Via Analogy, Wylie Z. Kasai
Poster, Performed: Understanding Public Opinions Of Authorship In Generative Artificial Intelligence Models Via Analogy, Wylie Z. Kasai
Dartmouth College Master’s Theses
Over the last decade, generative artificial intelligence models have advanced significantly and provided the public with several tools to create new works of art. However, the true authorship of these works has been debated due to their training on web-scraped data. Serving as an analogy to these larger models, Poster, Performed is an interactive artificial intelligence exhibition project that uses image assets submitted by the public to create poster compositions with custom image processing algorithms. During the course of a four-day exhibition, visitors were asked to identify the exhibition’s primary artist from five options: (1) participants who submitted image assets, …
(Meta-)Physical Artworks: Digital Augmentation In Art Observation, Macy A. Toppan
(Meta-)Physical Artworks: Digital Augmentation In Art Observation, Macy A. Toppan
Dartmouth College Master’s Theses
Augmented art— the subgenre of art that incorporates physical and digital artwork— is a rapidly growing field driven by advancing technology and a new generation for whom that tech is a given. Yet the presence of media like augmented and virtual reality in exhibition remains a controversial subject. Rather than focusing on the many theoretical debates about whether digital pieces can qualify as "good" art, we study it in practice through the eyes of the casual art observer. This paper highlights the audience in a within-participant study that asked viewers to take in a physical sculpture intentionally built with virtual …
A Bayesian Inversion For Emissions And Export Productivity Across The End-Cretaceous Boundary, Alexander A. Cox
A Bayesian Inversion For Emissions And Export Productivity Across The End-Cretaceous Boundary, Alexander A. Cox
Dartmouth College Master’s Theses
The end-Cretaceous mass extinction was marked by both the Chicxulub impact and the ongoing emplacement of the Deccan Traps flood basalt province. Both of these events perturbed the environment by the emission of climate-active volatiles, primarily CO2 and SO2. To understand the mechanism of extinction, we must disentangle the timing, duration, and intensity of volcanic and meteoritic environmental forcings. In this thesis, we used a parallel Markov chain Monte Carlo approach to invert for the aforementioned volatile emissions, export productivity, and remineralization from 67 to 65 million years ago using the LOSCAR (Long-term Ocean-atmosphere-Sediment CArbon cycle Reservoir) model. The parallel …
Probing And Enhancing The Reliance Of Transformer Models On Poetic Information, Almas Abdibayev
Probing And Enhancing The Reliance Of Transformer Models On Poetic Information, Almas Abdibayev
Dartmouth College Ph.D Dissertations
Transformer models have achieved remarkable success in the widest variety of domains, spanning not just a multitude of tasks within natural language processing, but also those in computer vision, speech, and reinforcement learning. The key to this success is largely attributed to the self-attention mechanism, particularly its ability to scale in performance as it grows in the number of parameters. Extensive effort has been underway to study the major linguistic properties learned by these models during the course of their pretraining. However, the role of certain finer linguistic phenomena present in language and their utilization by Transformers has not been …
Triple Helix: Ai-Artist-Audience Collaboration In A Performative Art Experience, Xuedan Zou
Triple Helix: Ai-Artist-Audience Collaboration In A Performative Art Experience, Xuedan Zou
Dartmouth College Master’s Theses
Imagine an art exhibition that morphs its content according to the audience’s experience like a chameleon, reflecting the audience’s mind and culture and turning the artist’s exhibition into the viewer’s. But when the viewers leave, the work fades back to the creator’s original work and waits for the next audience. In this project, my team introduced an interactive exhibition called "Triple Helix," where audience members were provided the opportunity to alter the artworks created by the artist, thus imbuing them with their own perspectives. This interactive exhibition was held at three physical-locations and online, and a comprehensive user study was …
Equilibrium And Quench-Dynamical Studies Of Ultracold Fermions In Ring-Shaped Optical Traps, Daniel Gordon Allman
Equilibrium And Quench-Dynamical Studies Of Ultracold Fermions In Ring-Shaped Optical Traps, Daniel Gordon Allman
Dartmouth College Ph.D Dissertations
The unique capability to precisely tune the few and many-body configurations of
ultracold Fermi gases provides a multi-dimensional platform for studying novel, ex-
otic aspects of quantum systems. These aspects include superfluid/superconducting
phenomena supported by potentially exotic pairing mechanisms, non-equilibrium and
critical dynamics, and proposed quantum sensing or computing applications based on
atomtronics.
Ring geometries provide natural arenas for probing transport properties of super-
fluids. Metastable states of quantized superfluid flow —persistent currents— exhibit
remarkable properties, and the manner in which they form is an incredibly rich sub-
ject. Studies of quenched superfluids demonstrate that persistent currents can form
from …
Rough Numbers And Variations On The Erdős--Kac Theorem, Kai Fan
Rough Numbers And Variations On The Erdős--Kac Theorem, Kai Fan
Dartmouth College Ph.D Dissertations
The study of arithmetic functions, functions with domain N and codomain C, has been a central topic in number theory. This work is dedicated to the study of the distribution of arithmetic functions of great interest in analytic and probabilistic number theory.
In the first part, we study the distribution of positive integers free of prime factors less than or equal to any given real number y>=1. Denoting by Phi(x,y) the count of these numbers up to any given x>=y, we show, by a combination of analytic methods and sieves, that Phi(x,y)<0.6x/\log y holds uniformly for all 3<=y<=sqrt{x}, improving upon an earlier result of the author in the same range. We also prove numerically explicit estimates of the de Bruijn type for Phi(x,y) which are applicable in wide ranges.
In the second part, we turn …
0.6x/\log>Energy-Aware Path Planning For Fixed-Wing Seaplane Uavs, Benjamin Atkinson Wolsieffer
Energy-Aware Path Planning For Fixed-Wing Seaplane Uavs, Benjamin Atkinson Wolsieffer
Dartmouth College Master’s Theses
Fixed-wing unmanned aerial vehicles (UAVs) are commonly used for remote sensing applications over water bodies, such as monitoring water quality or tracking harmful algal blooms. However, there are some types of measurements that are difficult to accurately obtain from the air. In existing work, water samples have been collected in situ either by hand, with an unmanned surface vehicle (USV), or with a vertical takeoff and landing (VTOL) UAV such as a multirotor. We propose a path planner, landing control algorithm, and energy estimator that will allow a low-cost and energy efficient fixed-wing UAV to carry out a combined remote …
Development Of Single-Crystalline And 3d-Printable Porous Organic Materials, Mingshi Zhang
Development Of Single-Crystalline And 3d-Printable Porous Organic Materials, Mingshi Zhang
Dartmouth College Ph.D Dissertations
Porous organic materials with designable structures, large surface areas, low densities, and unique electronic and optical properties have found widespread applications in adsorption, separation, energy storage, and catalysis. However, the majority of organic porous materials are synthesized as fluffy powders, which poses two fundamental challenges for them. Firstly, they lack a single-crystal structure at the microscopic scale, making it difficult to study the specific pore size, shape, and potential substrate binding sites at the atomic level and further establish the structure-property relationship. Secondly, they lack the general processing method and macroscopic shape design, making it difficult to manufacture suitable components …
Predictive Ai For The S&P 500 Index, Jacqueline Rose Perry
Predictive Ai For The S&P 500 Index, Jacqueline Rose Perry
Computer Science Senior Theses
Artificial intelligence has powerful applications in virtually every field, and the financial world is no exception. Utilizing various elements of artificial intelligence, this research aims to predict the future value of the S&P 500 index using numerous models, and in doing so, identify relevant features. More specifically, models that include combinations of historical data, public sentiment, and technical indicators were employed to predict the stock price one day and three days forward. To account for public opinion, the sentiment of tweets and news headlines from the beginning of 2015 through the end of 2019 was calculated using FinBERT, a pre-trained …
Self-Supervised Pretraining And Transfer Learning On Fmri Data With Transformers, Sean Paulsen
Self-Supervised Pretraining And Transfer Learning On Fmri Data With Transformers, Sean Paulsen
Dartmouth College Ph.D Dissertations
Transfer learning is a machine learning technique founded on the idea that knowledge acquired by a model during “pretraining” on a source task can be transferred to the learning of a target task. Successful transfer learning can result in improved performance, faster convergence, and reduced demand for data. This technique is particularly desirable for the task of brain decoding in the domain of functional magnetic resonance imaging (fMRI), wherein even the most modern machine learning methods can struggle to decode labelled features of brain images. This challenge is due to the highly complex underlying signal, physical and neurological differences between …
Anatoview: Using Interactive 3d Visualizations With Augmented Reality Support For Laypersons’ Medical Education In Informed Consent Processes, Michelle Chen
Dartmouth College Master’s Theses
AnatoView is an interactive multimedia educational application that visualizes medical procedures in three-dimensional (3D), augmented reality (AR) space. By providing visual and spatial information of medical procedures, AnatoView acts as a learning supplement for laypersons/patients in informed consent (IC) processes — wherein instructional content is traditionally limited to purely spoken explanations that lead to poor patient comprehension. We design a mixed study and conduct a randomized, controlled trial with 15 laypersons as participants: administering a traditional IC process to a control group, and an IC process supplemented by the use of AnatoView to experimental groups. As a primary outcome, medical …
Rhodium-Catalyzed Asymmetric Synthesis Of P-P And P-C Bonds, Sarah T. Chachula
Rhodium-Catalyzed Asymmetric Synthesis Of P-P And P-C Bonds, Sarah T. Chachula
Dartmouth College Ph.D Dissertations
Chapter 1: Synthesis, Structure, Dynamics, and Enantioface-Selective η3-Benzyl Coordination in the Chiral Rhodium Complexes Rh(diphos*)(η3-CH2Ph) Abstract: The rhodium benzyl complexes Rh(diphos*)(η3-CH2Ph) (1-14, diphos* = chiral bis(phosphine)) were prepared either by treatment of Rh(COD)(η3-CH2Ph) (15, COD = 1,5-cyclooctadiene) with diphos*, or from the reaction of [Rh(diphos*)(Cl)]2 (16- 20) with PhCH2MgCl. For C2-symmetric diphos*, observation of one set of NMR signals for complexes 1-12 suggested that the two diastereomers in which different 3-benzyl enantiofaces were coordinated to rhodium interconverted rapidly on the NMR time scale via suprafacial shifts; observation of five inequivalent aryl 1H NMR signals showed that antarafacial shifts were slow …
System-Characterized Artificial Intelligence Approaches For Cardiac Cellular Systems And Molecular Signature Analysis, Ziqian Wu
Dartmouth College Ph.D Dissertations
The dissertation presents a significant advancement in the field of cardiac cellular systems and molecular signature systems by employing machine learning and generative artificial intelligence techniques. These methodologies are systematically characterized and applied to address critical challenges in these domains. A novel computational model is developed, which combines machine learning tools and multi-physics models. The main objective of this model is to accurately predict complex cellular dynamics, taking into account the intricate interactions within the cardiac cellular system. Furthermore, a comprehensive framework based on generative adversarial networks (GANs) is proposed. This framework is designed to generate synthetic data that faithfully …
Say That Again: The Role Of Multimodal Redundancy In Communication And Context, Brandon Javier Dormes
Say That Again: The Role Of Multimodal Redundancy In Communication And Context, Brandon Javier Dormes
Cognitive Science Senior Theses
With several modes of expression, such as facial expressions, body language, and speech working together to convey meaning, social communication is rich in redundancy. While typically relegated to signal preservation, this study investigates the role of cross-modal redundancies in establishing performance context, focusing on unaided, solo performances. Drawing on information theory, I operationalize redundancy as predictability and use an array of machine learning models to featurize speakers' facial expressions, body poses, movement speeds, acoustic features, and spoken language from 24 TEDTalks and 16 episodes of Comedy Central Stand-Up Presents. This analysis demonstrates that it is possible to distinguish between these …
The Dilemma Of Disclosure: Designing Interpersonal Informatics Tools For Mood Tracking, Daniel Earl Westphal
The Dilemma Of Disclosure: Designing Interpersonal Informatics Tools For Mood Tracking, Daniel Earl Westphal
Computer Science Senior Theses
Mental health is a serious issue that affects people of all ages, but is especially prevalent amongst college age youth. In the 2020-2021 school year, researchers found that around 60% of college students met the criteria for at least one mental health condition, such as major depression or generalized anxiety disorder. Many digital interventions have been innovated in order to help address this issue. These range in type and functionality from teletherapy to medication tracking applications. Some of these digital interventions include social features that allow users to interact with other users, friends, family, or doctors; however, having social features …
Parameterization Of Cryosat-2 Radar Waveforms Across The Greenland Ice Sheet, Alexander Clark Ronan
Parameterization Of Cryosat-2 Radar Waveforms Across The Greenland Ice Sheet, Alexander Clark Ronan
Dartmouth College Master’s Theses
Geodetic surface mass balance calculations regularly rely on satellite radar altimeters such as CryoSat-2 to understand elevation and volume changes of the Greenland Ice Sheet (GrIS). However, the impact of changing GrIS shallow subsurface stratigraphic conditions on CryoSat-2 elevation products is poorly understood. We seek to investigate the long-term impacts of changing surface and shallow subsurface conditions on CryoSat-2 Level 2 elevation products derived from the Offset Center of Gravity (OCOG), Ocean - Customer Furnished Item (CFI), and University College London (UCL) Land-Ice retracking algorithms through the analysis of radar waveform characteristics. We further investigate time series from 2010 to …
Cosmological Vector Fields And Constraining The Neutrino Masses, Avery J. Tishue
Cosmological Vector Fields And Constraining The Neutrino Masses, Avery J. Tishue
Dartmouth College Ph.D Dissertations
In this thesis I explore two main topics: the role and consequences of cosmological vector fields, and new ideas for constraining fundamental physics with state-of-the-art experiments. These topics are disparate in content and technique but unified in their attempt to leverage novel approaches to better understand longstanding questions in cosmology. These questions, such as ``What is causing the universe to accelerate today?'' and ``What are the neutrino masses?'', underpin the modern cosmological paradigm. They play a key role in our understanding of cosmic history, the formation of structure, and the fate of our universe. Answers to or hints about these …
Information Diffusion In Online Social Networks: A Simulation Experiment, Maxwell Jacob Blum
Information Diffusion In Online Social Networks: A Simulation Experiment, Maxwell Jacob Blum
Quantitative Social Science Undergraduate Senior Theses
The advent of online social networks has completely transformed the way we communicate, with news, opinions, and ideas now spreading faster than ever before (Guille et al., 2013; Lee et al., 2022). That online social networks have a profound impact on the spread of information suggests further investigation of the relationship between network structure and information diffusion (Light & Moody, 2020). This honors thesis investigates degree assortativity – a measure of large-scale network structure that has often only been a footnote in relevant literature on infor- mation diffusion in online social networks – and its effect on the speed of …
The Flow Of Power: Addressing Asymmetric Flood Risk In The Upper Valley, Eric Vr Hryniewicz
The Flow Of Power: Addressing Asymmetric Flood Risk In The Upper Valley, Eric Vr Hryniewicz
Geography Undergraduate Senior Theses
Floods are the most damaging natural disasters in America. Land use change in upland watersheds can increase the probability and severity of floods (Bronstert, Niehoff, & Burger, 2002). When watersheds are divided by political and private property boundaries it leads to a misalignment of incentives in which downstream users lack recourse for upstream land use decisions contributing to flood risk. In this thesis, researchers interrogate the attributes of town officials and towns that determine what motivates town governments to act on flooding and what motivates and enables town officials to collaborate on planning and how do they collaborate in practice. …
Stereotypes And Language Models: Understanding How Language Models Encode Stereotypes, Debiasing Language Models, And Examining How Stereotypes Affect Conversations, Brian C. Wang
Computer Science Senior Theses
This thesis describes a variety of approaches in examining how language models encode stereotypes (understanding stereotypes from a model point-of-view), debiasing language models, and using language models to understand how stereotypes affect conversations (understanding stereotypes from a conversational point-of-view). We present a novel approach for textual clues analysis that makes language models more interpretable, combining the understanding of what stereotypes the internal structures of language models have encoded during their initial training (via attention-based analysis) and understanding what textual clues are most relevant to identifying stereotypes for models trained to detect stereotypes (via SHAP-based analysis). We find that different pre-trained …