Aspect-based sentiment analysis (ASBA) is a refined approach to sentiment analysis that aims to extract and classify sentiments based on specific aspects or features of a product, service, or entity. Unlike traditional sentiment analysis, which assigns a general sentiment score to entire reviews or texts, ABSA focuses on breaking down the text into individual components or aspects (e.g., quality, price, service) and evaluating the sentiment towards each. This allows for a more granular level of understanding of customer opinions, enabling businesses to pinpoint specific areas of strength and improvement. The process involves several key steps, including aspect extraction, sentiment classification, and aspect-level sentiment aggregation for a review paragraph or any other form that the users have provided. ABSA has significant applications in areas such as product reviews, social media monitoring, customer feedback analysis, and market research. By leveraging techniques from natural language processing (NLP) and machine learning, ABSA facilitates the extraction of valuable insights, enabling companies to make data-driven decisions that enhance customer satisfaction and optimize offerings. As ABSA evolves, it holds the potential to greatly improve personalized customer experiences by providing a deeper understanding of sentiment across various product aspects. In this work, we have analyzed the strength of LLMs for a complete cross-domain aspect-based sentiment analysis with the aim of defining the framework for certain products and using it for other similar situations. We argue that it is possible to that at an effectiveness of 92% accuracy for the Aspect Based Sentiment Analysis dataset of SemEval-2015 Task 12. Keywords: Aspect Extraction, Opinion Mining, Fine-grained Sentiment, Product Review Analysis, Aspect Polarity

Turn-taking is a fundamental aspect of conversation, but current Human-Robot Interaction (HRI) systems often rely on simplistic, silence-based models, leading to unnatural pauses and interruptions. This paper investigates, for the first time, the application of general turn-taking models, specifically TurnGPT and Voice Activity Projection (VAP), to improve conversational dynamics in HRI. These models are trained on human-human dialogue data using self-supervised learning objectives, without requiring domain-specific fine-tuning. We propose methods for using these models in tandem to predict when a robot should begin preparing responses, take turns, and handle potential interruptions. We evaluated the proposed system in a within-subject study against a traditional baseline system, using the Furhat robot with 39 adults in a conversational setting, in combination with a large language model for autonomous response generation. The results show that participants significantly prefer the proposed system, and it significantly reduces response delays and interruptions.

This paper explores the development of a multimodal sentiment analysis model that integrates text, audio, and visual data to enhance sentiment classification. The goal is to improve emotion detection by capturing the complex interactions between these modalities, thereby enabling more accurate and nuanced sentiment interpretation. The study evaluates three feature fusion strategies -- late stage fusion, early stage fusion, and multi-headed attention -- within a transformer-based architecture. Experiments were conducted using the CMU-MOSEI dataset, which includes synchronized text, audio, and visual inputs labeled with sentiment scores. Results show that early stage fusion significantly outperforms late stage fusion, achieving an accuracy of 71.87\%, while the multi-headed attention approach offers marginal improvement, reaching 72.39\%. The findings suggest that integrating modalities early in the process enhances sentiment classification, while attention mechanisms may have limited impact within the current framework. Future work will focus on refining feature fusion techniques, incorporating temporal data, and exploring dynamic feature weighting to further improve model performance.

We also want several types of topic shifts to Dialogue is at the core of human behaviour and happen. Even though oral face-to-face exchange being able to identify the topic at hand is crucial is the most complete form of dialogue, it is also to take part in conversation. Nevertheless, from a the most complicated to collect due to material and scientific point of view, the notion of topic is somewhat human constraints. Therefore we chose to collect elusive. Mittwoch et al. (2002) and Raymond our corpus through a written messaging tool similar (2004) focus on topic shift markers, while Howe to the one developed by Healey and Mills (2009).

Understanding emotions in videos is a challenging task. However, videos contain several modalities which make them a rich source of data for machine learning and deep learning tasks. In this work, we aim to improve video sentiment classification by focusing on two key aspects: the video itself, the accompanying text, and the acoustic features. To address the limitations of relying on large labeled datasets, we are developing a method that utilizes clustering-based semi-supervised pre-training to extract meaningful representations from the data. This pre-training step identifies patterns in the video and text data, allowing the model to learn underlying structures and relationships without requiring extensive labeled information at the outset. Once these patterns are established, we fine-tune the system in a supervised manner to classify the sentiment expressed in videos. We believe that this multi-modal approach, combining clustering with supervised fine-tuning, will lead to more accurate and insightful sentiment classification, especially in cases where labeled data is limited.

Conversational speech synthesis (CSS) aims to take the current dialogue (CD) history as a reference to synthesize expressive speech that aligns with the conversational style. Unlike CD, stored dialogue (SD) contains preserved dialogue fragments from earlier stages of user-agent interaction, which include style expression knowledge relevant to scenarios similar to those in CD. Note that this knowledge plays a significant role in enabling the agent to synthesize expressive conversational speech that generates empathetic feedback. However, prior research has overlooked this aspect. To address this issue, we propose a novel Retrieval-Augmented Dialogue Knowledge Aggregation scheme for expressive CSS, termed RADKA-CSS, which includes three main components: 1) To effectively retrieve dialogues from SD that are similar to CD in terms of both semantic and style. First, we build a stored dialogue semantic-style database (SDSSD) which includes the text and audio samples. Then, we design a multi-attribute retrieval scheme to match the dialogue semantic and style vectors of the CD with the stored dialogue semantic and style vectors in the SDSSD, retrieving the most similar dialogues. 2) To effectively utilize the style knowledge from CD and SD, we propose adopting the multi-granularity graph structure to encode the dialogue and introducing a multi-source style knowledge aggregation mechanism. 3) Finally, the aggregated style knowledge are fed into the speech synthesizer to help the agent synthesize expressive speech that aligns with the conversational style. We conducted a comprehensive and in-depth experiment based on the DailyTalk dataset, which is a benchmarking dataset for the CSS task. Both objective and subjective evaluations demonstrate that RADKA-CSS outperforms baseline models in expressiveness rendering. Code and audio samples can be found at: https://github.com/Coder-jzq/RADKA-CSS.

Detecting user frustration in modern-day task-oriented dialog (TOD) systems is imperative for maintaining overall user satisfaction, engagement, and retention. However, most recent research is focused on sentiment and emotion detection in academic settings, thus failing to fully encapsulate implications of real-world user data. To mitigate this gap, in this work, we focus on user frustration in a deployed TOD system, assessing the feasibility of out-of-the-box solutions for user frustration detection. Specifically, we compare the performance of our deployed keyword-based approach, open-source approaches to sentiment analysis, dialog breakdown detection methods, and emerging in-context learning LLM-based detection. Our analysis highlights the limitations of open-source methods for real-world frustration detection, while demonstrating the superior performance of the LLM-based approach, achieving a 16\% relative improvement in F1 score on an internal benchmark. Finally, we analyze advantages and limitations of our methods and provide an insight into user frustration detection task for industry practitioners.

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and tasks. However, spoken dialogue systems still lag behind in terms of naturalness. They tend to produce robotic interactions, with issues such as slow response times, overly generic or cautious replies, and a lack of natural rhythm and fluid turn-taking. This shortcoming is largely due to the over-reliance on the traditional cascaded design, which involve separate, sequential components, as well as the use of text as an intermediate representation. This paper propose a real-time, textless spoken dialogue generation model (RTTL-DG) that aims to overcome these challenges. Our system enables fluid turn-taking and generates responses with minimal delay by processing streaming spoken conversation directly. Additionally, our model incorporates backchannels, filters, laughter, and other paralinguistic signals, which are often absent in cascaded dialogue systems, to create more natural and human-like interactions. The implementations and generated samples are available in our repository: https://github.com/mailong25/rts2s-dg

Multimodal Sentiment Analysis (MSA) integrates diverse modalities(text, audio, and video) to comprehensively analyze and understand individuals' emotional states. However, the real-world prevalence of incomplete data poses significant challenges to MSA, mainly due to the randomness of modality missing. Moreover, the heterogeneity issue in multimodal data has yet to be effectively addressed. To tackle these challenges, we introduce the Modality-Invariant Bidirectional Temporal Representation Distillation Network (MITR-DNet) for Missing Multimodal Sentiment Analysis. MITR-DNet employs a distillation approach, wherein a complete modality teacher model guides a missing modality student model, ensuring robustness in the presence of modality missing. Simultaneously, we developed the Modality-Invariant Bidirectional Temporal Representation Learning Module (MIB-TRL) to mitigate heterogeneity.

As short text data in native languages like Hindi increasingly appear in modern media, robust methods for topic modeling on such data have gained importance. This study investigates the performance of BERTopic in modeling Hindi short texts, an area that has been under-explored in existing research. Using contextual embeddings, BERTopic can capture semantic relationships in data, making it potentially more effective than traditional models, especially for short and diverse texts. We evaluate BERTopic using 6 different document embedding models and compare its performance against 8 established topic modeling techniques, such as Latent Dirichlet Allocation (LDA), Non-negative Matrix Factorization (NMF), Latent Semantic Indexing (LSI), Additive Regularization of Topic Models (ARTM), Probabilistic Latent Semantic Analysis (PLSA), Embedded Topic Model (ETM), Combined Topic Model (CTM), and Top2Vec. The models are assessed using coherence scores across a range of topic counts. Our results reveal that BERTopic consistently outperforms other models in capturing coherent topics from short Hindi texts.