Ganesha Poornalatha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ganesha Poornalatha has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- K. B. Ajitha Shenoy
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India
4 shared publications - Chethan Sharma
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
2 shared publications Satarupa Biswas
Manipal Academy of Higher Education
2 shared publications- Abishek B. Rao
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
1 shared publication Akilesh C. Harti
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India
1 shared publication- Ankit Deepansh
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India
1 shared publication
Latest Publications
- Open Access
- 30 April 2026
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 40 (1)
A Human-Psychology-Informed Multi-Task Learning Framework for Robust Opinion Mining
- 30 April 2026
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 40 (1)
Open AccessA Human-Psychology-Informed Multi-Task Learning Framework for Robust Opinion Mining
- Open Access
- 5 March 2026
- Published by Elsevier in ICT Express
- Vol. 12 (3) , 593-609
Image restoration using deep learning techniques: A comprehensive review
- 5 March 2026
- Published by Elsevier in ICT Express
- Vol. 12 (3) , 593-609
Open AccessImage restoration using deep learning techniques: A comprehensive review
- Open Access
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 33252-33262
Leveraging Sentiment Analysis of Consumer Feedback for Data-Driven CRM in Digital Game Ecosystems
Companies in the digital age rely on Customer Relationship Management (CRM) to build loyalty and keep users engaged. Traditionally built around structured inputs such as transactional logs or survey results, CRM systems are now challenged by the overwhelming influx of unstructured, experience-driven feedback from digital forums, review platforms, and social media. This sudden shift introduces feedback that is both high in emotional expressiveness and rich in feature-level granularity, posing significant interpretation challenges for legacy CRM workflows. This problem is obvious in the gaming industry, where users actively and continuously respond to game updates, service breakdowns, or balance issues through real-time public discourse. The domain-oriented tools are needed to manage this type of feedback to parse multi-dimensional opinion data. The proposed framework is specifically designed for gaming-related CRM applications. The current framework considers various online user reviews to process them through a dual pipeline architecture, considering the Removal of Personally Identifiable Information (PII), linguistic normalization, and ontology-driven tagging. The rule-based approach was used in the product pipeline using feature proximity. A hybrid NLP approach was employed for the service path. The sentiment tags were initialized by zero-shot RoBERTa, and a high-confidence-based fine-tuning was carried out using Sentiment140. Final predictions were reassigned and evaluated against pseudo-gold standards. Various interactive dashboards were designed to visualize the insights obtained from the framework, that asists CRM teams to act on player sentiment with feature-level and time-sensitive clarity.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 33252-33262
Open AccessLeveraging Sentiment Analysis of Consumer Feedback for Data-Driven CRM in Digital Game Ecosystems
Companies in the digital age rely on Customer Relationship Management (CRM) to build loyalty and keep users engaged. Traditionally built around structured inputs such as transactional logs or survey results, CRM systems are now challenged by the overwhelming influx of unstructured, experience-driven feedback from digital forums, review platforms, and social media. This sudden shift introduces feedback that is both high in emotional expressiveness and rich in feature-level granularity, posing significant interpretation challenges for legacy CRM workflows. This problem is obvious in the gaming industry, where users actively and continuously respond to game updates, service breakdowns, or balance issues through real-time public discourse. The domain-oriented tools are needed to manage this type of feedback to parse multi-dimensional opinion data. The proposed framework is specifically designed for gaming-related CRM applications. The current framework considers various online user reviews to process them through a dual pipeline architecture, considering the Removal of Personally Identifiable Information (PII), linguistic normalization, and ontology-driven tagging. The rule-based approach was used in the product pipeline using feature proximity. A hybrid NLP approach was employed for the service path. The sentiment tags were initialized by zero-shot RoBERTa, and a high-confidence-based fine-tuning was carried out using Sentiment140. Final predictions were reassigned and evaluated against pseudo-gold standards. Various interactive dashboards were designed to visualize the insights obtained from the framework, that asists CRM teams to act on player sentiment with feature-level and time-sensitive clarity.
- Open Access
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 143688-143712
A Comprehensive Review of Recent Advances in Multimodal Multimedia Indexing and Retrieval
With the exponential growth of digital data across several domains, multimedia retrieval has emerged as a very critical research area. While much development has been witnessed in feature extraction, indexing methods, and deep learning-based retrieval models, many challenges persistently hamper the creation of efficient and scalable multimedia retrieval systems. This review systematically analyzes recent research in multimedia retrieval, highlighting key methodologies, findings, and limitations across various studies. The major gaps identified include the semantic disparity between low-level features and high-level semantics, as well as challenges of large datasets, privacy and security concerns, and the explainability of deep learning models. Besides, challenges on noisy and imbalanced data, multimodal data sources, and a lack of standardized benchmarking frameworks further limit the performance of existing systems. This paper comprehensively presents these gaps and proposes future research directions to bridge them, thereby directing the development of more robust, scalable, and user-centered multimedia retrieval systems. To overcome persistent challenges in versatility, semantic alignment, and trustworthiness, we introduce a unified framework that seamlessly integrates multimodal semantic fusion, explainable AI, privacy-preserving learning, and continual adaptation for robust and future-ready multimedia retrieval.
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 143688-143712
Open AccessA Comprehensive Review of Recent Advances in Multimodal Multimedia Indexing and Retrieval
With the exponential growth of digital data across several domains, multimedia retrieval has emerged as a very critical research area. While much development has been witnessed in feature extraction, indexing methods, and deep learning-based retrieval models, many challenges persistently hamper the creation of efficient and scalable multimedia retrieval systems. This review systematically analyzes recent research in multimedia retrieval, highlighting key methodologies, findings, and limitations across various studies. The major gaps identified include the semantic disparity between low-level features and high-level semantics, as well as challenges of large datasets, privacy and security concerns, and the explainability of deep learning models. Besides, challenges on noisy and imbalanced data, multimodal data sources, and a lack of standardized benchmarking frameworks further limit the performance of existing systems. This paper comprehensively presents these gaps and proposes future research directions to bridge them, thereby directing the development of more robust, scalable, and user-centered multimedia retrieval systems. To overcome persistent challenges in versatility, semantic alignment, and trustworthiness, we introduce a unified framework that seamlessly integrates multimodal semantic fusion, explainable AI, privacy-preserving learning, and continual adaptation for robust and future-ready multimedia retrieval.
- Open Access
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 170360-170371
Dynamic Advertisement Pricing and Bidding Optimization: An Integrated Machine Learning and Auction Framework
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 170360-170371
Open AccessDynamic Advertisement Pricing and Bidding Optimization: An Integrated Machine Learning and Auction Framework
- Open Access
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 169606-169613
Transformers and Attention: Decoding and Understanding of Aspect-Based Opinions in User-Generated Contents
Aspect-based opinion mining has become a significant information extraction technique based on natural language processing, driven by the growing volume of online user-generated content. This approach aims to determine the opinion polarity of specific aspects within a given context. The existing models primarily target explicit aspects, often neglecting the identification of implicitly mentioned aspect-based opinion polarity. Consequently, these existing models result in low classification accuracy and struggle to identify multiple aspects within a specific context. This paper proposes an aspect-based attention model (AAM) to address these limitations. We integrate a pre-trained BERT model with an attention mechanism to perform aspect detection. The AAMmodel is trained and evaluated on the benchmarked SemEval-2014 Task 4 dataset. Experimental results demonstrate that the proposed AAM model outdoes other existing methods. Additionally, the robustness and generalizability of the proposed model are calculated using raw textual datasets.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 169606-169613
Open AccessTransformers and Attention: Decoding and Understanding of Aspect-Based Opinions in User-Generated Contents
Aspect-based opinion mining has become a significant information extraction technique based on natural language processing, driven by the growing volume of online user-generated content. This approach aims to determine the opinion polarity of specific aspects within a given context. The existing models primarily target explicit aspects, often neglecting the identification of implicitly mentioned aspect-based opinion polarity. Consequently, these existing models result in low classification accuracy and struggle to identify multiple aspects within a specific context. This paper proposes an aspect-based attention model (AAM) to address these limitations. We integrate a pre-trained BERT model with an attention mechanism to perform aspect detection. The AAMmodel is trained and evaluated on the benchmarked SemEval-2014 Task 4 dataset. Experimental results demonstrate that the proposed AAM model outdoes other existing methods. Additionally, the robustness and generalizability of the proposed model are calculated using raw textual datasets.
- Open Access
- 28 September 2024
- Published by Qeios Ltd
Review of: "Exploring the Impact of Analytics-Driven Forecasting on Spotify Technology's Financial Health: An Exploratory Data Analysis"
The topic looks interesting. However, the following are the concerns: * The literature review mentions machine learning-based methods, tools, results, etc. It would be better to mention the limitations in the existing work mentioned in the literatu...
- 28 September 2024
- Published by Qeios Ltd
Open AccessReview of: "Exploring the Impact of Analytics-Driven Forecasting on Spotify Technology's Financial Health: An Exploratory Data Analysis"
The topic looks interesting. However, the following are the concerns: * The literature review mentions machine learning-based methods, tools, results, etc. It would be better to mention the limitations in the existing work mentioned in the literatu...
- Open Access
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 85551-85564
A Novel Multiclass Object Detection Dataset Enriched With Frequency Data
Video analysis has attracted the attention of many researchers because of the growing need for multimedia information retrieval for computer vision applications. Content based retrieval and object-based video retrieval are challenging because of the poor feature representation of the objects and the low number of multiclass video datasets available. Even though there have been significant advances in generic object detection & information retrieval tasks, performance of object based indexing & retrieval falls due to the low number of representative video dataset and lack of information on the frequency of objects. In order to facilitate the progress of multimedia information retrieval in the field of computer vision related application research, we present the multiclass object detection datasets. This dataset consists of 732 videos from YouTube with 5 object classes and each video is about 2 minutes long and total size of the dataset being approximately 8.5 GB. In this article, we will provide the baseline evaluation results of two of the latest object detection algorithms used to evaluate the newly created multidimensional object detection dataset. The paper presents the performance metrics of object detection methods at various time frames. Accuracy remains consistently high, ranging from 93.98% at the 5th frame to 84.17% at the 30th frame, suggesting a generally strong ability to make correct predictions. The dataset is publicly available at https://drive.google.com/file/d/1BHVsB38vbu9LUY03XlFWY2o_gxEiIKY7/view?usp=sharing .
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 85551-85564
Open AccessA Novel Multiclass Object Detection Dataset Enriched With Frequency Data
Video analysis has attracted the attention of many researchers because of the growing need for multimedia information retrieval for computer vision applications. Content based retrieval and object-based video retrieval are challenging because of the poor feature representation of the objects and the low number of multiclass video datasets available. Even though there have been significant advances in generic object detection & information retrieval tasks, performance of object based indexing & retrieval falls due to the low number of representative video dataset and lack of information on the frequency of objects. In order to facilitate the progress of multimedia information retrieval in the field of computer vision related application research, we present the multiclass object detection datasets. This dataset consists of 732 videos from YouTube with 5 object classes and each video is about 2 minutes long and total size of the dataset being approximately 8.5 GB. In this article, we will provide the baseline evaluation results of two of the latest object detection algorithms used to evaluate the newly created multidimensional object detection dataset. The paper presents the performance metrics of object detection methods at various time frames. Accuracy remains consistently high, ranging from 93.98% at the 5th frame to 84.17% at the 30th frame, suggesting a generally strong ability to make correct predictions. The dataset is publicly available at https://drive.google.com/file/d/1BHVsB38vbu9LUY03XlFWY2o_gxEiIKY7/view?usp=sharing .
- Open Access
- 12 June 2024
- Published by Qeios Ltd
Review of: "Study of the Problems of Determining Public Opinion of the Israeli-Palestinian War in Social Networks"
Limited technical contribution in terms of novelty. The result looks trivial. Advised to explore some statistical methods/models to further analyze the results. Advised to elaborate on the data set and on neutral cases where the number of positive an...
- 12 June 2024
- Published by Qeios Ltd
Open AccessReview of: "Study of the Problems of Determining Public Opinion of the Israeli-Palestinian War in Social Networks"
Limited technical contribution in terms of novelty. The result looks trivial. Advised to explore some statistical methods/models to further analyze the results. Advised to elaborate on the data set and on neutral cases where the number of positive an...
- Open Access
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 25906-25916
Opinion Mining Using Multi-Dimensional Analysis
This review addresses emerging literature in the field of Opinion Mining with a particular emphasis on user-generated textual content. The focus is on the various tasks involved in Opinion Mining, which satisfies the comprehension of the essential criteria and methodologies that should be considered prior to embraking on the task. The paper provides an in-depth analysis of benchmarked datasets, widely-used feature sets, algorithms, techniques, open-source tools, challenges, real-world applications, and insights into various dimensions of Opinion Mining. The findings have both theoretical and practical implications, as it highlights the significance of Opinion Mining of textual content in comprehensive society. This review covers both technical and real-world knowledge and offers a comprehensive understanding of available open-source tools that are used in real-time.
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 25906-25916
Open AccessOpinion Mining Using Multi-Dimensional Analysis
This review addresses emerging literature in the field of Opinion Mining with a particular emphasis on user-generated textual content. The focus is on the various tasks involved in Opinion Mining, which satisfies the comprehension of the essential criteria and methodologies that should be considered prior to embraking on the task. The paper provides an in-depth analysis of benchmarked datasets, widely-used feature sets, algorithms, techniques, open-source tools, challenges, real-world applications, and insights into various dimensions of Opinion Mining. The findings have both theoretical and practical implications, as it highlights the significance of Opinion Mining of textual content in comprehensive society. This review covers both technical and real-world knowledge and offers a comprehensive understanding of available open-source tools that are used in real-time.