Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

A Quantum Computing based Approach for Sentiment Analysis in Bilateral Conversations

Níyazí Furkan Bar, Musa Yenilmez, Sedef Aksu, Mehmet Karaköse

Published Feb 21, 2024• 5 citations
Publisher

Abstract

Sentiment analysis finds widespread applications in health, marketing, finance, stock markets, media, and politics. To analyze attitudes and emotions in textual data, handling large datasets and significant computational power is essential. Traditional computing methods struggle with the growing data volume, prompting interest in quantum computing as a promising alternative with its inherent high-speed processing capacity. This study focuses on sentiment analysis applied to texts derived from bilateral conversation dialogues. The primary objective is to categorize emotions within the text as positive, neutral, or negative, while concurrently identifying the speaker. To achieve this, a novel quantum-classical hybrid approach is proposed. The quantum side of this approach includes the variational quantum circuit (VQC). On the classical side, preprocessing of the data set, feature extraction with a model containing LSTM, and optimizing the parameters of VQC are performed. The proposed approach was trained and tested using a data set containing bilateral conversations. As a result of the tests, the proposed approach achieved a higher accuracy rate compared to studies using the classical approach. Thus, the effectiveness of the proposed approach is confirmed.

DOI
10.1109/it61232.2024.10475718

Related papers

SentiQNF: A Novel Approach to Sentiment Analysis Using Quantum Algorithms and Neuro-Fuzzy Systems

Kshitij Dave, Nouhaila Innan, Bikash K. Behera +3 more

Sentiment analysis (SA) is an essential component of natural language processing (NLP) and is used to analyze sentiments, attitudes, and emotional tones in various contexts. It provides valuable insights into public opinion, customer feedback, and user experiences. Researchers have developed various classical machine learning (ML) and neuro-fuzzy approaches to address the exponential growth of data and the complexity of language structures in SA. However, these approaches often fail to determine the optimal number of clusters, interpret results accurately, handle noise or outliers efficiently, and scale effectively to high-dimensional data. In addition, they are frequently insensitive to input variations. In this article, we propose a novel hybrid approach for SA called the quantum fuzzy neural network (QFNN), which leverages quantum properties and incorporates a fuzzy layer to overcome the limitations of classical SA algorithms. In this study, we test the proposed approach on two Twitter datasets: the Coronavirus Tweets Dataset (CVTD) and the General Sentimental Tweets Dataset (GSTD), and compare it with classical and hybrid algorithms. The results show that QFNN outperforms all classical, quantum, and hybrid algorithms, achieving 100% and 90% accuracy in the case of CVTD and GSTD, respectively. Furthermore, QFNN demonstrates its robustness against six different noise models, providing the potential to tackle the computational complexity associated with SA on a large scale in a noisy environment. The proposed approach expedites sentiment data processing and precisely analyzes different forms of textual data, thus improving sentiment classification and insights associated with SA.

arXiv:2412.12731•IEEE Transactions on Computational Social Systems•Aug 7, 2025•13 citations

Quantum AI in Speech Emotion Recognition

Michael Norval, Zenghui Wang

Abstract This study explores Quantum AI’s potential in enhancing Speech Emotion Recognition (SER) systems. Our primary objective is to evaluate the performance of quantum-inspired algorithms compared to classical machine-learning approaches in accurately identifying and classifying emotions from speech signals. We hypothesise that quantum computing techniques can improve the efficiency and accuracy of emotion recognition, particularly in handling complex, highdimensional acoustic data. We developed a hybrid quantum-classical model that combines quantum-inspired neural networks with traditional feature extraction techniques. Our approach utilises quantum circuits for data encoding and quantum variational algorithms for classification. We implemented quantum versions of support vector machines (QSVM) and quantum approximate optimisation algorithms (QAOA) for emotion classification tasks. These quantum methods were compared against a hybrid Convolutional Neural Network and Long Short Term (LSTM). The hybrid network is called a Convolutional Long Short Term network(CLSTM). The study employed a custom dataset for speech emotion recognition. We prepossessed the audio data to extract relevant acoustic features, including mel-frequency cepstral coefficients (MFCCs), pitch, and energy. In contrast, our implemented quantum-inspired model for this corpus showed lower performance, with the highest training accuracy of 30%, struggling with most emotions but performing best with ’Trust’. These varied results across different implementations suggest that while Quantum AI techniques show promise in advancing speech emotion recognition, their effectiveness may depend on the specific dataset, language, and model architecture used. Finally, the speed of a simulated quantum network is shown to outperform current methods in terms of matrix multiplication by leaps and bounds.

Entropy•Nov 26, 2025•5 citations

Hybrid Quantum-Classical Neural Network for Multimodal Multitask Sarcasm, Emotion, and Sentiment Analysis

Arpan Phukan, Santanu Pal, Asif Ekbal

Sarcasm detection in unimodal or multimodal setting is a very complex task. Sarcasm, emotion, and sentiment are related to each other, and hence any multitask model could be an effective way to leverage the interdependence among these tasks. In order to better represent these clandestine associations, we avoid solely relying on traditional machine learning methods to encode the relationships between the modalities. In this article, we propose a hybrid quantum model that banks upon the low computational complexity and robust representational power of a variational quantum circuit (VQC) and the tried and tested dense neural network to tackle sentiment, emotion, and sarcasm classification simultaneously. We empirically establish that the quantum properties like superposition, entanglement, and interference will better capture and replicate not only the cross-modal interactions between text, acoustics, and visuals but also the correlations between the three responses. We consider the extended MUStARD dataset to evaluate our proposed hybrid model. The results show that our proposed hybrid quantum framework yields more promising results for the primary task of sarcasm detection with the help of the two secondary classification tasks,viz.sentiment and emotion.

IEEE Transactions on Computational Social Systems•May 7, 2024•28 citations

Exploring Sentiment Analysis on Social Media through Quantum Computing

Lateshwari

This research delves into the realm of sentiment analysis applied to Twitter data, utilizing quantum computing to advance its accuracy and efficiency. The escalating complexity and abundance of textual content on social media platforms have presented challenges for conventional computational methods in effectively gauging sentiments. Quantum computing, renowned for its capacity in parallel processing and intricate data analysis, presents a novel avenue to enhance sentiment analysis. This study employs quantum-inspired algorithms to process and examine sentiments within real-time Twitter data, contributing to a more comprehensive comprehension of user opinions and emotions expressed on the platform.

International Journal of Intelligent Systems and Applications in Engineering•Jul 9, 2024•0 citations

Senti-Quant: Quantum Computing Driven Sentiment Analysis for Faster Opinion Generation

Amandeep Singh, Basanti Pal Nandi, Poonam Ahuja Narang +1 more

The employment of quantum computing in the sentiment analysis seems to provide remarkable accuracy and efficiency in classifying the positive and negative sentiments. The traditional methods find it difficult to deal with large volume of data which requires high training time. Hence, quantum computing holds an advantage over traditional methodologies. In the proposed Senti-Quan model the extracted sentiment scores are encoded into a quantum circuit. Various quantum gates like Hadamard, Pauli-X, CNOT, Rotation gates are implemented to get the detailed pattern of the data. The measured quantum results when compared with the actual sentiment provide an increased F1 score than other models working on Sentiment140 dataset without any requirement of training time. The average processing time of Senti-Quan model comes out to be 27 times faster than the other traditional techniques

International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)•Sep 18, 2025•0 citations

A Comparison of Traditional Natural Language Processing Methods for Emotion Recognition Using Quantum Computing

Srirajarajeswari Thota, Sandeep Kumar Dash

Emotion Recognition plays an important role in recognizing human behavior. Human behavior may be represented in text, speech, and facial expressions. In traditional form, natural language processing known as NLP is used to extract features to evaluate emotions. With the evolution of Quantum Computing, Quantum Machine learning often called QML is one of the research areas used to evaluate emotions. This paper is designed to compare traditional ML models with QML models to analyze the sentiments and emotions of multimodal data. Here, NLP techniques are used for preprocessing. A hybrid model is built by combining NLP and QML. The preprocessed data are transmitted into quantum circuits for computation, and its results are compared with conventional machine learning models. This evaluation identifies QML as a promising future as it is useful for large and complex data sets with high dimensions. This study highlights the potential of QML in NLP and outlines the challenges such as encoding and hardware limitations.

International Conference on Machine Learning and Autonomous Systems (ICMLAS)•Mar 10, 2025•3 citations
Sentiment analysis finds widespread applications in health, marketing, finance, stock markets, media, and politics. To analyze attitudes and emotions in textual data, handling large datasets and significant computational power is essential. Traditional computing methods struggle with the growing data volume, prompting interest in quantum computing as a promising alternative with its inherent high-speed processing capacity. This study focuses on sentiment analysis applied to texts derived from bilateral conversation dialogues. The primary objective is to categorize emotions within the text as positive, neutral, or negative, while concurrently identifying the speaker. To achieve this, a novel quantum-classical hybrid approach is proposed. The quantum side of this approach includes the variational quantum circuit (VQC). On the classical side, preprocessing of the data set, feature extraction with a model containing LSTM, and optimizing the parameters of VQC are performed. The proposed approach was trained and tested using a data set containing bilateral conversations. As a result of the tests, the proposed approach achieved a higher accuracy rate compared to studies using the classical approach. Thus, the effectiveness of the proposed approach is confirmed.
Sentiment analysis (SA) is an essential component of natural language processing (NLP) and is used to analyze sentiments, attitudes, and emotional tones in various contexts. It provides valuable insights into public opinion, customer feedback, and user experiences. Researchers have developed various classical machine learning (ML) and neuro-fuzzy approaches to address the exponential growth of data and the complexity of language structures in SA. However, these approaches often fail to determine the optimal number of clusters, interpret results accurately, handle noise or outliers efficiently, and scale effectively to high-dimensional data. In addition, they are frequently insensitive to input variations. In this article, we propose a novel hybrid approach for SA called the quantum fuzzy neural network (QFNN), which leverages quantum properties and incorporates a fuzzy layer to overcome the limitations of classical SA algorithms. In this study, we test the proposed approach on two Twitter datasets: the Coronavirus Tweets Dataset (CVTD) and the General Sentimental Tweets Dataset (GSTD), and compare it with classical and hybrid algorithms. The results show that QFNN outperforms all classical, quantum, and hybrid algorithms, achieving 100% and 90% accuracy in the case of CVTD and GSTD, respectively. Furthermore, QFNN demonstrates its robustness against six different noise models, providing the potential to tackle the computational complexity associated with SA on a large scale in a noisy environment. The proposed approach expedites sentiment data processing and precisely analyzes different forms of textual data, thus improving sentiment classification and insights associated with SA.
Abstract This study explores Quantum AI’s potential in enhancing Speech Emotion Recognition (SER) systems. Our primary objective is to evaluate the performance of quantum-inspired algorithms compared to classical machine-learning approaches in accurately identifying and classifying emotions from speech signals. We hypothesise that quantum computing techniques can improve the efficiency and accuracy of emotion recognition, particularly in handling complex, highdimensional acoustic data. We developed a hybrid quantum-classical model that combines quantum-inspired neural networks with traditional feature extraction techniques. Our approach utilises quantum circuits for data encoding and quantum variational algorithms for classification. We implemented quantum versions of support vector machines (QSVM) and quantum approximate optimisation algorithms (QAOA) for emotion classification tasks. These quantum methods were compared against a hybrid Convolutional Neural Network and Long Short Term (LSTM). The hybrid network is called a Convolutional Long Short Term network(CLSTM). The study employed a custom dataset for speech emotion recognition. We prepossessed the audio data to extract relevant acoustic features, including mel-frequency cepstral coefficients (MFCCs), pitch, and energy. In contrast, our implemented quantum-inspired model for this corpus showed lower performance, with the highest training accuracy of 30%, struggling with most emotions but performing best with ’Trust’. These varied results across different implementations suggest that while Quantum AI techniques show promise in advancing speech emotion recognition, their effectiveness may depend on the specific dataset, language, and model architecture used. Finally, the speed of a simulated quantum network is shown to outperform current methods in terms of matrix multiplication by leaps and bounds.
Sarcasm detection in unimodal or multimodal setting is a very complex task. Sarcasm, emotion, and sentiment are related to each other, and hence any multitask model could be an effective way to leverage the interdependence among these tasks. In order to better represent these clandestine associations, we avoid solely relying on traditional machine learning methods to encode the relationships between the modalities. In this article, we propose a hybrid quantum model that banks upon the low computational complexity and robust representational power of a variational quantum circuit (VQC) and the tried and tested dense neural network to tackle sentiment, emotion, and sarcasm classification simultaneously. We empirically establish that the quantum properties like superposition, entanglement, and interference will better capture and replicate not only the cross-modal interactions between text, acoustics, and visuals but also the correlations between the three responses. We consider the extended MUStARD dataset to evaluate our proposed hybrid model. The results show that our proposed hybrid quantum framework yields more promising results for the primary task of sarcasm detection with the help of the two secondary classification tasks,viz.sentiment and emotion.
This research delves into the realm of sentiment analysis applied to Twitter data, utilizing quantum computing to advance its accuracy and efficiency. The escalating complexity and abundance of textual content on social media platforms have presented challenges for conventional computational methods in effectively gauging sentiments. Quantum computing, renowned for its capacity in parallel processing and intricate data analysis, presents a novel avenue to enhance sentiment analysis. This study employs quantum-inspired algorithms to process and examine sentiments within real-time Twitter data, contributing to a more comprehensive comprehension of user opinions and emotions expressed on the platform.
The employment of quantum computing in the sentiment analysis seems to provide remarkable accuracy and efficiency in classifying the positive and negative sentiments. The traditional methods find it difficult to deal with large volume of data which requires high training time. Hence, quantum computing holds an advantage over traditional methodologies. In the proposed Senti-Quan model the extracted sentiment scores are encoded into a quantum circuit. Various quantum gates like Hadamard, Pauli-X, CNOT, Rotation gates are implemented to get the detailed pattern of the data. The measured quantum results when compared with the actual sentiment provide an increased F1 score than other models working on Sentiment140 dataset without any requirement of training time. The average processing time of Senti-Quan model comes out to be 27 times faster than the other traditional techniques
Emotion Recognition plays an important role in recognizing human behavior. Human behavior may be represented in text, speech, and facial expressions. In traditional form, natural language processing known as NLP is used to extract features to evaluate emotions. With the evolution of Quantum Computing, Quantum Machine learning often called QML is one of the research areas used to evaluate emotions. This paper is designed to compare traditional ML models with QML models to analyze the sentiments and emotions of multimodal data. Here, NLP techniques are used for preprocessing. A hybrid model is built by combining NLP and QML. The preprocessed data are transmitted into quantum circuits for computation, and its results are compared with conventional machine learning models. This evaluation identifies QML as a promising future as it is useful for large and complex data sets with high dimensions. This study highlights the potential of QML in NLP and outlines the challenges such as encoding and hardware limitations.