Mitigating Semantic Drift: Evaluating LLMs’ Efficacy in Psychotherapy through MI Dialogue Summarization Leveraging MITI Code
IEEE
Our study evaluates LLMs in psychotherapy, addressing issues of empathy, bias, and semantic drift. Using expert-annotated MI dialogues and a MITI-based two-stage scheme, we test models through progressive prompting. Findings reveal how LLMs interpret complex psychological constructs and offer best practices for safe, precise therapeutic use.
Advanced Meta-Analysis of Facial Expression Recognition using Spatio-TS NN Models
2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE) · Sep 22, 2025
The research presented at the 2025 International Conference on Intelligent Computing and Knowledge Extraction (ICICKE) introduces an advanced meta-analysis of Facial Expression Recognition (FER) using Spatio-Temporal Siamese Neural Network (Spatio-TS NN) models. Addressing persistent challenges such as overfitting, illumination variance, pose differences, and demographic bias in FER, the study proposes a systematic framework integrating bilateral filtering for preprocessing, geometric landmark-based feature extraction, and Adaptive Butterfly Optimization (ABOA) for feature selection. The refined features are then trained on Spatio-TS NN models, enabling robust temporal–spatial learning and superior classification accuracy. Experimental findings demonstrate a remarkable 99.15% recognition rate, outperforming GRU and BiLSTM-based architectures. Beyond its methodological rigor, the research holds significant implications for real-world applications in healthcare, security, human-computer interaction, and affective computing, positioning Spatio-TS NN as a state-of-the-art approach in automated emotion recognition.
https://ieeexplore.ieee.org/document/11136294
Unlocking LLMs: Addressing Scarce Data and Bias Challenges in Mental Health and Therapeutic Counselling
ACL Anthology · May 18, 2025
Large language models (LLMs) have shown promising capabilities in healthcare analysis but face several challenges like hallucinations, parroting, and bias manifestation. These challenges are exacerbated in complex, sensitive, and low-resource domains. Therefore, in this work, we introduce IC-AnnoMI, an expert-annotated motivational interviewing (MI) dataset built upon AnnoMI, by generating in-context conversational dialogues leveraging LLMs, particularly ChatGPT. IC-AnnoMI employs targeted prompts accurately engineered through cues and tailored information, taking into account therapy style (empathy, reflection), contextual relevance, and false semantic change. Subsequently, the dialogues are annotated by experts, strictly adhering to the Motivational Interviewing Skills Code (MISC), focusing on both the psychological and linguistic dimensions of MI dialogues. We comprehensively evaluate the IC-AnnoMI dataset and ChatGPT’s emotional reasoning ability and understanding of domain intricacies by modeling novel classification tasks employing several classical machine learning and current state-of-the-art transformer approaches. Finally, we discuss the effects of progressive prompting strategies and the impact of augmented data in mitigating the biases manifested in IC-AnnoM. Our contributions provide the MI community with not only a comprehensive dataset but also valuable insights for using LLMs in empathetic text generation for conversational therapy in supervised settings.
https://aclanthology.org/2024.nlpaics-1.26/
Granted Copyright
The Art of Effective Communication: Mastering Interpersonal Skills for Personal & Professional Success.
Innovation, Science and Economic Development Canada
- Innovation, Science and Economic Development Canada
- Innovation, Sciences et Développement économique Canada
- Office de la propriété intellectuelle du Canada Canadian Intellectual Property Office · Dec 31, 2024
7th International Scientific Conference “Baltic Applied Astroinformatics and Space data Processing” (BAASP) and organized by Engineering Research Institute Ventspils International Radio Astronomy Centre"
BAASP, Latvia Ventspils University of Applied Sciences · Sep 17, 2021
Astroinformatics in India reflects a remarkable journey from ancient sky-watching traditions to modern data-driven astronomy. India’s early astronomers, from Aryabhata to Bhaskara II, laid mathematical foundations that now empower contemporary computational methods. Today, with ISRO’s expanding missions, large observatories, and rapid growth of machine learning, India integrates vast astronomical datasets into cutting-edge research. Astroinformatics unifies observation, computation, and analytics enhancing planetary studies, space-weather modelling, and deep-sky exploration. From ancient star charts to present-day AI-enabled pipelines, India’s progress demonstrates how heritage and high technology together shape the nation’s evolving astronomical future.
Deep Learning–Driven Remote Sensing Models for Predictive Analysis of Eutrophication and Algal Bloom Dynamics in Freshwater Ecosystems
Natural and Engineering Sciences 10 (3), 844-854
Harmful algal blooms (HABs) and eutrophication became one of the most important problems in global environmental issues that has a grievous threat to freshwater habitats, biodiversity, drinking water security, and socio-economic stability. The methods of traditional in-situ sampling and in-laboratory analysis are also valid, but have a limited scope of their usefulness due to their high labour-intensive nature and the lack of real-time or large-scale analyses. Current developments in satellite-based Earth observation systems and the usage of deep learning algorithms have now offered the benefit of high-resolution, scalable, and rapid monitoring of aquatic systems. This research paper compiles a client remote sensing system based on the deep learning methodology to identify, measure, and predict the dynamics of eutrophication, and HAB growth on the basis of the multispectral and hyperspectral images of the Sentinel-2, Landsat-8/9, MODIS, and PRISMA satellites. The suggested system will use convoluted neural networks (CNNs), long short-term memory (LSTM) networks, the Vision Transformers (ViTs) systems and a combination of the CNN/LSTM systems that can achieve the learning of spectral-spatial representations and spatial features and temporal evolving of the blooms respectively. The most important water quality indicators, such as chlorophyll- a (Chl-a) concentration, turbidity, total suspended solids and nitrogen- phosphorus proxies are estimated with the help of regression and classification models that are trained on harmonised satellite data and field-measured ground truth. The experimental outcomes on several freshwater lakes and reservoirs show that the hybrid deep learning model has more than 94% classification accuracy on the level of the bloom intensity, and a root-mean-square error (RMSE) of Chl-a prediction is less than 7 percent, which is better than conventional machine learning baselines. The framework is also capable of 3- to 7-day predictions of the behaviour of blossoms, which could greatly benefit the early-warning and resource management systems. This research can contribute greatly to remote sensing-met water quality monitoring and interventions through offering an operationally versatile, cost-effective and scalable solution to the increasing effects of eutrophication and HAB events, providing effective decision-support tools to environmental agency, population health departments and freshwater resource managers in the US and beyond.
https://nesciences.com/article/72928/
Reattach Treatment Implementation for Developing Coping Skills among Maladjusted Teenagers
Journal for ReAttach Therapy and Developmental Diversities 6 (9s), 1450-1454
Reattachment treatment is an effective rehabilitation-based approach for addressing major psychological and behavioral issues. This study aims to strengthen the therapeutic framework by outlining essential interventions that enhance its credibility. Using a secondary data collection method, information was gathered from reliable sources such as Google Scholar journals and scholarly articles to ensure authenticity and accuracy.
Based on the review, speech therapy is emphasized to address communication difficulties among maladjusted adolescents. The study also highlights the crucial role of parents and teachers in skill development and behavioral improvement. Additionally, the SAGE Recovery Framework is presented as a comprehensive model for addressing key challenges faced by teenagers.
Other 7 Patents & Copyrights Granted
Indian & International Patents
Details will be shared on request...!!
