Abstract

Background Protest music has historically shaped collective identity and transformed struggle into shared resistance. While prior research has examined its usage and impact (Bianchi, 2018; Mondak, 1988), little is known about the linguistic and acoustic markers that drive its perceptual distinctiveness. This study investigates whether protest songs exhibit consistent structural and expressive patterns that differentiate them from non-protest music. Methodology We analyzed 458 protest songs extracted from Wikipedia (Jiang & Jin, 2022) and 370 non-protest songs matched by time period. The following linguistic features were computed from lyrics: repetition rate (repeated bigrams/trigrams per lyrical line), lexical diversity (TTR = unique word types divided by total word tokens, reflecting vocabulary variation), unique word ratio (unique word types divided by lyrical lines, capturing how many new words appear per line), valence (emotional positivity or negativity), and rhyme density (number of rhyming word pairs per line). We also analyzed acoustic features obtained from the Spotify API: speechiness (degree of spoken-word content), danceability (rhythmic stability; a stable rhythm makes the brain follow the beats), acousticness (likelihood of acoustic over electric timbre), and instrumentalness (absence of vocals). Results Protest songs showed significantly higher rhyme density, repetition rate, greater unique word ratio, lower lexical diversity, and more negative valence than non-protest songs (all p < .001). A logistic regression classifier trained on these features achieved 90% accuracy, confirming their discriminative strength. Protest songs had significantly higher values for all acoustic features as well (p < .001). Deep learning was used to classify protest and non-protest songs; using lyrics with XLRoBERTa (94% accuracy) outperformed the audio model CLAP (89% accuracy). However, both are significant, so we can infer both the message and medium are responsible for the distinctive features of protest music. Genre may act as a confounding factor, as protest songs tend to cluster in rock, metal, country, and hip-hop, unlike non-protest songs which skew toward pop and disco. This limitation can be addressed in future work. Discussion The highly negative valence suggests that protest songs revolve mostly around negative themes. High repetition aids attention and recall. Low lexical diversity with high unique word ratio reflects figurative, chant-like repetition—where key phrases recur for impact, while new words enrich new lines. High rhyme density indicates phonetic structuring and lyrical crafting. Protest songs exhibit high speechiness, indicating a spoken-word style delivery. Their high danceability reflects stable, rhythmic patterns that facilitate collective engagement. Elevated acousticness suggests a preference for raw, organic textures. Meanwhile, high instrumentalness points to moments of vocal sparseness, where instruments alone carry emotional weight. Conclusion This study sheds light on how protest songs use structural and acoustic cues to create emotionally charged experiences. It contributes to a deeper understanding of the perceptual features of protest music and offers empirical grounding of the key distinguishing features. These findings deepen our understanding of the structural and expressive elements of protest music, providing valuable insights for research in music, linguistics, and social movements.

Abstract

The global rise of football analytics has rapidly transformed how clubs make strategic decisions (morgulev2018sports,). However, in India, the adoption of analytics remains constrained by institutional resistance, infrastructural limitations, and cultural barriers—challenges that grassroots innovation and low-cost data solutions have the potential to overcome. Despite the increasing popularity of the Indian Super League (scroll2020isl,; chatterjee2021isl,), resource scarcity and fragmented governance continue to hinder the widespread adoption and impact of analytics. This mixed-methods study explores how informal, decentralized analytics communities—comprising amateur analysts and Twitter-based “data sleuths”—navigate these constraints through peer mentorship and grassroots innovation. Drawing on extensive digital ethnography, participant observation, and interviews, the study illustrates how these informal networks mitigate data scarcity, limited digital infrastructure, and institutional indifference while fostering skill development and professional growth. Building on these insights, the paper proposes HCI interventions such as decentralized knowledge platforms to facilitate structured, cross-border peer mentorship and low-cost data solutions—including AI-assisted player tracking and mobile analytics dashboards—rooted in principles of frugal innovation (shauloff2023ai,). These interventions aim to bridge the data divide, support inclusive technical engagement in sport, and enhance analytics-driven decision-making in resource-constrained environments. This paper contributes to HCIxB’s focus on cross-border collaboration by highlighting how community-driven technological adaptation in the Global South can foster meaningful participation, skill-building, and long-term sustainability through informal learning networks and scalable, context-sensitive tools (vashistha2017cve,; nawaz2021farming,).

Abstract

The shotgun sequencing process involves fragmenting a long DNA sequence (input string) into numerous shorter, unordered, and overlapping segments (referred to as reads). The reads are sequenced and later aligned to reconstruct the original string. Viewing the sequencing process as the read-phase of a DNA storage system, the information-theoretic capacity of noise-free shotgun sequencing has been characterized in literature. Motivated by the base-wise quality scores available in practical sequencers, a recent work considered the shotgun sequencing channel with erasures, in which the symbols in the reads are assumed to contain random erasures. Achievable rates for this channel were identified. In the present work, we obtain a converse for this channel. The arguments for the proof involve a careful analysis of a genie-aided decoder, which knows the correct ordering of the reads. The converse is not tight in general; however, it meets the achievability result asymptotically in some channel parameters.

Abstract

Dual-arm robotic grasping is crucial for handling large objects that require stable and coordinated manipulation. While single-arm grasping has been extensively studied, datasets tailored for dual-arm settings remain scarce. We introduce a large-scale dataset of 16 million dual-arm grasps, evaluated under improved force-closure constraints. Additionally, we develop a benchmark dataset containing 300 objects with approximately 30,000 grasps, evaluated in a physics simulation environment, providing a better grasp quality assessment for dual-arm grasp synthesis methods. Finally, we demonstrate the effectiveness of our dataset by training a Dual-Arm Grasp Classifier network that outperforms the state of-the-art methods by 15%, achieving higher grasp success rates and improved generalization across objects.

Abstract

Lane detection is critical for Advanced Driver Assistance Systems (ADAS) in autonomous vehicles. Deep learning models offer high accuracy but are computationally demanding for resource-constrained edge platforms, while lightweight image processing algorithms are energy-efficient but often falter in complex scenarios. This paper presents RL-ALMS (Reinforcement Learning-based Adaptive and Lightweight Model Selection), a framework that dynamically switches between deep learning and image processing lane detection models in electric vehicles (EVs). RL-ALMS employs a contextual multi-armed bandit with Thompson sampling to intelligently select the optimal model based on road conditions, battery state, and accuracy needs. The novelty lies in its system-level integration of a battery-aware reward function and a sustainability-driven selection mechanism, specifically designed to balance real-time detection accuracy with long-term EV energy constraints. Experimental results on an edge computing platform demonstrate RL-ALMS achieves 90.3% average accuracy over a 50km journey while maintaining 81.2% battery reserve, significantly outperforming fixed high-accuracy (battery depletion) and energy-efficient (64.5% accuracy) strategies. RL-ALMS maintains consistent performance across diverse conditions, representing a practical advancement for energy-constrained, real-time lane detection in EVs.

Abstract

This study addresses the critical challenge of data scarcity in machine translation for Indian languages, particularly given their morpholog- ical complexity and limited parallel data. We investigate an effective strategy to maximize the utility of existing data by generating nega- tive samples from positive training instances us- ing a progressive perturbation approach. This is used to align the model with preferential data using Kahneman-Tversky Optimization (KTO). Comparing it against traditional Su- pervised Fine-Tuning (SFT), we demonstrate how generating negative samples and leverag- ing KTO enhances data efficiency. By creat- ing rejected samples through progressively per- turbed translations from the available dataset, we fine-tune the Llama 3.1 Instruct 8B model using QLoRA across 16 language directions, in- cluding English, Hindi, Bangla, Tamil, Telugu, and Santali. Our results show that KTO-based preference alignment with progressive pertur- bation consistently outperforms SFT, achieving significant gains in translation quality with an average BLEU increase of 1.84 to 2.47 and CHRF increase of 2.85 to 4.01 compared to SFT for selected languages, while using the same positive training samples and under simi- lar computational constraints. This highlights the potential of our negative sample genera- tion strategy within KTO, especially in low- resource scenarios.

Abstract

Automatic detection and classification of stuttering events remain a challenging problem in speech processing, particularly due to the variability of disfluency types and the scarcity of large annotated datasets. This paper presents a signal processing-based approach for stuttering classification that avoids the data-intensive requirements of machine learning models. Our method focuses on syllable-level analysis using key acoustic parameters such as energy patterns, pitch contours, spectral stability, and temporal features, implemented through rule-based classification with predefined thresholds. The methodology involves automatic syllable segmentation followed by rule-based classification using thresholds on acoustic features. The dataset comprises annotated read and spontaneous speech from 106 Kannada-speaking adults, including 26 new participants evaluated during clinical trials. Three certified Speech-Language Pathologists (SLPs) conducted perceptual evaluations, and system outputs were validated using intraclass correlation (ICC), yielding strong agreement (textgreater 0.82) across stuttering types. The system achieved classification accuracies of 89% for blocks, 83% for repetitions, and 81% for prolongations. However, the system has several limitations: it relies on static threshold values, exhibits sensitivity to noise, and lacks automated severity grading. Additionally, generalizability across languages and speaking conditions requires further exploration. Machine learning models such as SVM, TDNN, and LSTM were trained and achieved a performance of around 30 to 60% accuracy. Our approach offers high interpretability, low computational cost, and real-time feasibility compared to machine learning methods. Future work will focus on adaptive thresholding, noise-robust processing, and hybrid approaches integrating signal processing with lightweight learning-based refinement.

Abstract

Natural walking offers high immersion in Virtual Reality (VR) but is constrained by physical space. Overlapping architectures, which reuse physical space, are a potential solution. Building on foundational principles of Architecturally Consistent Maze Generation in VR [1], we developed,implemented, and evaluated the Procedural Overlapping Maze System (POMS). POMS procedurally generates and prunes right-angled, overlapping maze corridors in real-time, enabling continuous natural walking in footprints ≥ 4x4m. This paper presents a controlled, between-group empirical evaluation (N=17 matched pairs) comparing POMS against a spatially equivalent static maze in an 8x8m tracked area using an Oculus Quest 3. Participants performed a time-constrained navigation task. We investigated effects on user engagement (time-on-task), usability (User Experience Questionnaire - UEQ), presence (igroup Presence Questionnaire - iPQ), and cybersickness (Simulator Sickness Questionnaire - SSQ). We hypothesized POMS would lead to increased time-on-task (H1), and that its dynamic nature would not negatively impact user experience, aiming for UEQ, iPQ, and SSQ outcomes comparable to a static environment (H2-H4). Results indicated no statistically significant differences in UEQ (H2) or iPQ (H3) between conditions, supporting our hypotheses that POMS could maintain these experiential qualities. Surprisingly, regarding cybersickness (H4), the increase in Oculomotor, Disorientation, and Total SSQ symptoms was significantly smaller in the POMS condition compared to the Static condition, while there was no significant difference for Nausea. This finding demonstrates an unexpected and substantial comfort benefit with POMS, exceeding our initial hypothesis of mere comparability. While POMS did not show a statistically significant increase in time-on-task (H1) in this study, a numerical trend suggesting longer engagement was observed. The markedly improved comfort achieved with POMS strongly suggests that such architectures have the potential to facilitate longer interaction periods, warranting further investigation into task design to fully leverage this benefit. These findings highlight that procedurally overlapping architectures like POMS can enable extended natural walking, not only without degrading core experiential qualities,but also by significantly enhancing user comfort.

Abstract

Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. The relational context between toxic phrases in captions and memes, as well as visual concepts in memes enhance the model's reasoning capabilities. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively. Given the contextual complexity of the toxicity detection task, our approach showcases the significance of learning from both explicit (i.e. KG) as well as implicit (i.e. LVLMs) contextual cues incorporated through a hybrid neurosymbolic approach. This is crucial for real-world applications where accurate and scalable recognition of toxic content is critical for creating safer online environments.

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their tendency to memorize training data raises concerns regarding privacy, copyright compliance, and security, particularly in cases involving Personally Identifiable Information (PII). Effective machine unlearning techniques are essential to mitigate these risks, yet existing methods remain underdeveloped for LLMs due to their open-ended output space. In this work, we apply the Adaptive Representation Misdirection Unlearning (RMU) technique to unlearn sensitive information from LLMs. Through extensive experiments, we analyze the effects of unlearning across different decoder layers to determine the most effective regions for sensitive information removal. Our technique ranked 4th on the official leaderboard of both 1B parameter and 7B parameter models.