Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics. Sentiment analysis is a typical example of such domains. In the last few years, by leveraging the modeling power of quantum probability (a non-classical probability stemming from quantum mechanics methodology) and deep neural networks, a range of novel quantum-cognitively inspired models for sentiment analysis have emerged and performed well. This survey presents a timely overview of the latest developments in this fascinating cross-disciplinary area. We first provide a background of quantum probability and quantum cognition at a theoretical level, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis. Then, recent quantum-cognitively inspired models are introduced and discussed in detail, focusing on how they approach the key challenges of the sentiment analysis task. Finally, we discuss the limitations of the current research and highlight future research directions.
Quantum theory, originally proposed as a physical theory to describe the motions of microscopic particles, has been applied to various non-physics domains involving human cognition and decision-making that are inherently uncertain and exhibit certain non-classical, quantum-like characteristics. Sentiment analysis is a typical example of such domains. In the last few years, by leveraging the modeling power of quantum probability (a non-classical probability stemming from quantum mechanics methodology) and deep neural networks, a range of novel quantum-cognitively inspired models for sentiment analysis have emerged and performed well. This survey presents a timely overview of the latest developments in this fascinating cross-disciplinary area. We first provide a background of quantum probability and quantum cognition at a theoretical level, analyzing their advantages over classical theories in modeling the cognitive aspects of sentiment analysis. Then, recent quantum-cognitively inspired models are introduced and discussed in detail, focusing on how they approach the key challenges of the sentiment analysis task. Finally, we discuss the limitations of the current research and highlight future research directions.
This paper presents SentiQNN (Sentiment Quantum Neural Network), a novel quantum-inspired neural network architecture specifically designed for sentiment analysis tasks in natural language processing. SentiQNN leverages quantum computing principles including superposition, entanglement, and quantum measurement to enhance traditional neural network capabilities for text classification. The model incorporates complex-valued embeddings, quantum mixture operations, and multi-task learning with sentiment lexicon integration to achieve superior performance in sentiment classification tasks. Through extensive experimentation across multiple benchmark datasets, SentiQNN demonstrates state-of-the-art performance with 88.11% accuracy, outperforming traditional classical approaches by 3-7%. The architecture introduces innovative quantum state preparation layers, quantum circuit operations, and quantum measurement mechanisms specifically optimized for natural language understanding. Our comprehensive evaluation reveals that quantum-inspired approaches can significantly enhance sentiment analysis performance while maintaining computational efficiency. The findings contribute to the emerging field of quantum machine learning and provide a foundation for future research in quantum-enhanced natural language processing systems.
Language model is a fundamental research topic in areas related to natural language processing. In recent years, researchers have proposed quantum language models based on the probability theory of quantum mechanics. This paper aims to review the research motivation and the current progress of constructing various quantum language models. First, it reviews the research problems of classical language models. Then, it introduces some quantum language models in information retrieval and speech processing, as well as an end-to-end quantum language model based on neural network architecture. By analyzing the advantages and disadvantages of each quantum language model considered here, taking into account the essential connection between quantum mechanics and neural networks, we outline our vision for future research directions.
The quantum cognition research programme concerns the application of quantum probability theory(the rules for how to assign probabilities to events from quantum mechanics, without the physics) tocognitive modeling. We review quantum cognitive models in several areas of psychology, includingconjunction/ disjunction fallacies in probabilistic judgment, conceptual combinations, similarity, order effects on judgments, causal inference, the disjunction effect in decision making, measurement and interference effects on judgments and decisions, memory, perception, and other judgment anddecision-making applications. For each area, we first present the empirical findings that have motivated the application of quantum models, emphasizing any characteristics which are particularly puzzling or have resisted coherent theoretical explanations previously; we then discuss the quantum cognitive models, noting the key features of the models that help explain the empirical data; we finally cast a critical eye on the models and explore comparisons with non-quantum models.
Quantum theory has inspired many new ideas for understanding Cognition and decision making. Given the nascent state of this field, many new challenges still remain. What are the strengths and unique contributions of these ideas? What are likely next steps in its development? How can it be applied to practical problems in cognitive science? Is this a rational or an irrational system of reasoning? What, if any, are its connections to neuroscience? Should the hard problem of consciousness be considered? These are questions that we try to address in this chapter, albeit at times in a limited way. We end with a debate with a fictitious skeptic (actually previous reviewers) of these ideas. Let us start by reviewing what we have covered so far. Contributions to cognition and decision We begin by summarizing the conclusions reached in previous chapters regarding the usefulness of quantum theory for modelling phenomena in cognition and decision. Chapter 1 provided some motivation and Chapter 2 provided a theoretical introduction to quantum theory. Chapter 3 presented a quantum model to account for question order effects on survey research. An exact and parameter-free test was derived from the model, which produced surprisingly accurate predictions for results obtained from three different large Gallup poll survey studies. Chapter 4 described a quantum model of probability judgments to account for findings that produce violations of classic probability theory, including conjunction and disjunction fallacies and order effects on inference.
The representation and processing of concepts is one of the hardest challenges in cognitive science. While computer scientists and engineers have focused on developing advances for particular tasks, philosophers and cognitive scientists have focused on elucidating the structural nature of meaning. A remarkable bridge between these two limited-success approaches can be found in behavioral research, since, in a variety of tasks, humans process information at a conceptual level in a way that is incompatible with classical probability and fuzzy set theory. Recently, attempts have been made to use mathematical schemes founded on quantum structures as alternative approaches. For this reason, the application of quantum structures to this type of phenomena has received increasing attention. The quantum approach allows to faithfully model a number of non-classical deviations observed in experimental data. Moreover, it shows that genuine quantum theoretical notions, such as contextuality, superposition, emergence, and entanglement, are powerful epistemic tools to understand and represent cognitive phenomena. In this thesis, we identify the limitations of classical theories to handle some important cognitive tasks, and introduce the fundamentals of the quantum cognitive approach to concepts. Next, we perform a mathematical analysis of current concept combination models and develop an extension that allows for concrete representations of multiple exemplars simultaneously. Our analysis indicates that a superposition of logical reasoning and a specific form of non-logical reasoning, where non-logical reasoning is dominant, allows to faithfully represent the experimental data. Therefore, the non-logical reasoning introduced by this model represents an important but unexplored form of reasoning in humans. In addition, we develop novel experimental methodologies to identify quantum conceptual structures for concept combinations in the context of natural language processing and psychological experiments. Namely, we present a methodology to build entangled concepts represented as sets of words with respect to a corpus of text, and present a computational and psychological methodology to discern if a collection of concepts behaves statistically as a collection of quantum or classical particles. Using both methodologies we have identified a significant presence of quantum conceptual structure in the context of natural language processing and psychological experiments.
Quantum probability theory, originally developed in the context of quantum mechanics, has increasingly been applied to social sciences to explain decision-making, cognition, and collective behavior. Unlike classical probability models, which assume pre-existing and well-defined preferences, quantum models incorporate superposition, interference, and non-commutativity to capture the contextual dependence and measurement effects observed in human decisions. This paper systematically explores the theoretical foundations of quantum probability in social sciences, discusses model construction techniques, and reviews empirical findings supporting its application. By examining case studies in quantum cognition, quantum game theory, and quantum voting, we illustrate how quantum approaches provide alternative explanations for phenomena such as order effects, measurement-induced attitude shifts, and collective polarization. The paper also discusses the methodological challenges and limitations of quantum social science, emphasizing the need for rigorous experimental validation and interdisciplinary collaboration. Finally, we highlight the potential for integrating quantum probability models with emerging technologies such as quantum computing and artificial intelligence, opening new avenues for social science research and policy applications.