Multimodal Sentiment Analysis Method Based on Hierarchical Adaptive Feature Fusion Network

We present a case study as part of a work-in-progress project about multimodal sentiment analysis on historic German plays, taking Emilia Galotti by G. E. Lessing as our initial use case. We analyze the textual version and an audio version (audio book). We focus on ready-to-use sentiment analysis methods: For the textual component, we implement a naive lexicon-based approach and another approach that enhances the lexicon by means of several NLP methods. For the audio analysis, we use the free version of the Vokaturi tool. We compare the results of all approaches and evaluate them against the annotations of a human expert, which serves as a gold standard. For our use case, we can show that audio and text sentiment analysis behave very differently: textual sentiment analysis tends to predict sentiment as rather negative and audio sentiment as rather positive. Compared to the gold standard, the textual sentiment analysis achieves accuracies of 56% while the accuracy for audio sentiment analysis is only 32%. We discuss possible reasons for these mediocre results and give an outlook on further steps we want to pursue in the context of multimodal sentiment analysis on historic plays.

Implicit emotions are often expressed through implicit and weak clues between modalities due to the lack of explicit emotional feature words, representing a significant challenge for multimodal sentiment analysis. In order to improve implicit emotion recognition, this paper proposes a multimodal sentiment analysis method that integrates KAN and the modal dynamic fusion mechanism. This method first introduces the KAN structure to construct a modal feature encoder to enhance the emotional expression ability of features. Then, the emotional contribution weight of each modality is calculated using the difference between the unimodal and multimodal sentiment scores, and the cross-attention mechanism guided by the main modality is used for feature fusion. Experiments on four datasets, CH-SIMS, CH-SIMSv2, MOSI, and MOSEI, show that the proposed method significantly outperforms the mainstream model in multiple indicators, especially when dealing with samples with implicit or ambiguous emotional expressions. The results verify the effectiveness of enhancing feature encoding capabilities and utilizing modal asymmetry information in implicit sentiment analysis.

Modality translation-based multimodal sentiment analysis under uncertain missing modalities

Multimodal sentiment analysis (MMSA) is a research method that extracts effective information from heterogeneous modal information. Then, MMSA processes the multimodal data and performs sentiment analysis. Along with big data and machine learning development, multimodal sentiment analysis has become a hot research direction in multimodal learning and natural language processing. Although various feature extraction methods and information fusion methods have been continuously proposed, challenges exist in MMSA research. First, in terms of feature extraction, pre-trained models trained with many data sets can obtain higher quality features, but research on how to use these feature extraction methods to extract the best features is still needed. Currently, the more popular feature fusion methods do not focus on the interaction between multiple modal information and the retention of basic information. To overcome these problems a multimodal sentiment analysis model utilizes text features as core modal features, using video and audio modal features as auxiliary modal features, multimodal feature modality attention mechanism to extract the intrinsic connection between different modalities. The attention mechanism uses the features of video modality and audio modality as the focus and then enhances the text modality with the fusion of video modality and modality. To improve the quality of extracted features, this method chooses the transfer learning training method and uses the pre-trained model for processing. This research uses the CMU-MOSI dataset to test the proposed method. Experimental results show that the performance of the proposed model in emotion score prediction and emotion classification tasks exceeds traditional methods and baseline methods.

With the widespread application of social media, the multimodal fusion feature of "text + image" in user-generated content has become a dominant form. Therefore, sentiment analysis based on multimodal social media images and texts is an important research topic today. However, sentiment analysis faces three major challenges: enhancing image modality expression, bridging the cross-modal semantic gap, and improving the ability to model complex texts. This paper reviews five typical multimodal sentiment analysis methods proposed in the past two years. These methods are categorized into image enhancement, semantic alignment, and large model integration based on the types of problems they primarily address. A comparative analysis of their technical paths, performance, and application scenarios is conducted to understand the research focus of each type of model, identify their shortcomings and challenges, and propose a cross-category fusion technology solution by integrating existing model methods. An integrated framework of "universal semantic encoding + dynamic modality adaptation + cross-scenario calibration" is constructed to improve the generalization and robustness of models, providing directions for future research on multimodal social media image-text sentiment analysis.

Multimodal sentiment analysis and emotion recognition represent a major research direction in natural language processing (NLP). With the rapid development of online media, people often express their emotions on a topic in the form of video, and the signals it transmits are multimodal, including language, visual, and audio. Therefore, the traditional unimodal sentiment analysis method is no longer applicable, which requires the establishment of a fusion model of multimodal information to obtain sentiment understanding. In previous studies, scholars used the feature vector cascade method when fusing multimodal data at each time step in the middle layer. This method puts each modal information in the same position and does not distinguish between strong modal information and weak modal information among multiple modalities. At the same time, this method does not pay attention to the embedding characteristics of multimodal signals across the time dimension. In response to the above problems, this paper proposes a new method and model for processing multimodal signals, which takes into account the delay and hysteresis characteristics of multimodal signals across the time dimension. The purpose is to obtain a multimodal fusion feature emotion analysis representation. We evaluate our method on the multimodal sentiment analysis benchmark dataset CMU Multimodal Opinion Sentiment and Emotion Intensity Corpus (CMU-MOSEI). We compare our proposed method with the state-of-the-art model and show excellent results.

Multimodal sentiment analysis aims to harvest people’s opinions or attitudes from multimedia data through fusion techniques. However, existing fusion methods cannot take advantage of the correlation between multimodal data but introduce interference factors. In this paper, we propose an Interactive Transformer and Soft Mapping based method for multimodal sentiment analysis. In the Interactive Transformer layer, an Interactive Multihead Guided-Attention structure composed of a pair of Multihead Attention modules is first utilized to find the mapping relationship between multimodalities. Then, the obtained results are fed into a Feedforward Neural Network. The Soft Mapping layer consisting of stacking Soft Attention module is finally used to map the results to a higher dimension to realize the fusion of multimodal information. The proposed model can fully consider the relationship between multiple modal pieces of information and provides a new solution to the problem of data interaction in multimodal sentiment analysis. Our model was evaluated on benchmark datasets CMU-MOSEI and MELD, and the accuracy is improved by 5.57% compared with the baseline standard.

Multimodal aspect-based sentiment analysis (MABSA) is an essential task in the field of sentiment analysis, which still confronts several critical challenges. The first challenge is how to effectively capture key information within both image and text features to enhance the recognition and understanding of complex sentiment expressions. The second challenge is how to achieve cross-modal alignment of multi-granularity text features and image features. The third challenge is how to narrow the semantic gap between image modality and text modality through effective cross-modal feature fusion. To address these issues, a framework that leverages external knowledge and multi-granularity image and text features (EKMG) is proposed. Firstly, an external knowledge enhanced semantic extraction module is introduced to fuse external knowledge with image features and text features, thereby capturing the key information from texts and images. Secondly, we design a multi-granularity image-text contrastive learning module. This module initially introduces a graph attention network and a novel cross-modal fusion mechanism to align image features and text features at multiple granularities. Additionally, the module employs an image-text contrastive learning strategy to narrow the semantic gap between different modalities. Experimental results on two public benchmark datasets demonstrate that EKMG achieves significant performance improvements compared to state-of-the-art baseline models.

The Multimodal Sentiment Analysis Challenge (MuSe) 2024 addresses two contemporary multimodal affect and sentiment analysis problems: In the Social Perception Sub-Challenge (MuSe-Perception), participants will predict 16 different social attributes of individuals such as assertiveness, dominance, likability, and sincerity based on the provided audio-visual data. The Cross-Cultural Humor Detection Sub-Challenge (MuSe-Humor) dataset expands upon the Passau Spontaneous Football Coach Humor (Passau-SFCH) dataset, focusing on the detection of spontaneous humor in a cross-lingual and cross-cultural setting. The main objective of MuSe 2024 is to unite a broad audience from various research domains, including multimodal sentiment analysis, audio-visual affective computing, continuous signal processing, and natural language processing. By fostering collaboration and exchange among experts in these fields, the MuSe 2024 endeavors to advance the understanding and application of sentiment analysis and affective computing across multiple modalities. This baseline paper provides details on each sub-challenge and its corresponding dataset, extracted features from each data modality, and discusses challenge baselines. For our baseline system, we make use of a range of Transformers and expert-designed features and train Gated Recurrent Unit (GRU)-Recurrent Neural Network (RNN) models on them, resulting in a competitive baseline system. On the unseen test datasets of the respective sub-challenges, it achieves a mean Pearson's Correlation Coefficient (ρ) of 0.3573 for MuSe-Perception and an Area Under the Curve (AUC) value of 0.8682 for MuSe-Humor.

Since the research of sentiment analysis is mostly concentrated in the field of sentiment analysis on Weibo, and there is less research on sentiment analysis of financial text, this thesis proposes a financial sentiment analysis model based on pre-training and TextCNN. First, the pre-trained model is used to initially extract the emotional features of the text. It can extract text features well, and can extract information between words at arbitrary intervals when processing text sequences. Then use the improved TextCNN to construct a sentiment analysis network to further extract the sentiment features of the text, effectively identify the sentiment of the text, and complete the sentiment analysis of financial text. This thesis conducts experiments on a balanced corpus data set based on financial texts, and compares it with other classic sentiment analysis algorithms. Experimental results show that the proposed method works best in the field of financial text sentiment analysis.

Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the main reason is that real-world applications can only access the text outputs by the automatic speech recognition (ASR) models, which may be with errors because of the limitation of model capacity. Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment analysis models directly. To address this problem, we propose the sentiment word aware multimodal refinement model (SWRM), which can dynamically refine the erroneous sentiment words by leveraging multimodal sentiment clues. Specifically, we first use the sentiment word position detection module to obtain the most possible position of the sentiment word in the text and then utilize the multimodal sentiment word refinement module to dynamically refine the sentiment word embeddings. The refined embeddings are taken as the textual inputs of the multimodal feature fusion module to predict the sentiment labels. We conduct extensive experiments on the real-world datasets including MOSI-Speechbrain, MOSI-IBM, and MOSI-iFlytek and the results demonstrate the effectiveness of our model, which surpasses the current state-of-the-art models on three datasets. Furthermore, our approach can be adapted for other multimodal feature fusion models easily 1 .

Multimodal sentiment analysis is an extended approach to traditional language-based sentiment analysis, which uses other relevant modality data. Multimodal sentiment analysis usually applies visual, textual, and acoustic representations for sentiment prediction. Recently, various data fusion methodologies have been proposed for multimodal sentiment analysis. In most cases, textual modality plays a major role, and visual and acoustic modalities are used as auxiliary sources for multimodal sentiment analysis. However, in general multimedia such as video, text transcripts of an individual's speech are not provided. Research on an audio-visual sentiment analysis methodology that does not depend on text modality is essential for multimodal sentiment analysis in real-world industrial applications. Therefore, it is important to improve audio-visual sentiment analysis because it currently exhibits lower performance than multimodal sentiment analysis, including text modality. In this paper, we propose heterogeneous modality transfer learning (HMTL) to utilize the knowledge of aligned text data as a source modality in transfer learning to improve audio-visual sentiment analysis performance. Our approach uses a decoder and adversarial learning techniques to reduce the gap between the source and target modalities in the embedded space for multimodal representation. Our proposed methodology experimentally outperformed recent unimodal and bimodal audio-visual sentiment analysis achievements.

Integrating color cues to improve multimodal sentiment analysis in social media

Multimodal sentiment analysis (MSA) has recently encountered two major challenges: non‐textual modalities are often affected by noise, and sentiment intensity differences are difficult to capture. To address these issues, we propose a Sentiment Intensity Contrastive Text‐Enhanced Fusion Network (SICTEF Net), which achieves deep collaboration among text, audio, and visual modalities through three key mechanisms. First, a grouped‐channel‐attention based Feature Enhancement Module (EMA) is designed to mitigate modality‐specific noise and emphasize emotion‐sensitive cues by combining spatial–channel interaction mapping with dual‐branch attention fusion. Second, a text‐centered cross‐modal fusion mechanism is introduced, where bidirectional multi‐head self‐attention and a residual‐enhanced encoder jointly enable complementary mappings between text and non‐text modalities, thereby producing intermediate representations that preserve semantic primacy while incorporating fine‐grained complementary information. Third, a sentiment‐intensity weighted contrastive learning strategy dynamically assigns weights to positive and negative sample pairs according to their sentiment intensity differences, allowing the model to more precisely distinguish samples with varying degrees of similarity in the embedding space. Experimental evaluation on the CMU‐MOSI and CMU‐MOSEI datasets demonstrates that SICTEF Net consistently outperforms state‐of‐the‐art baselines in binary accuracy, F1 score, seven‐class accuracy, mean absolute error (MAE), and Pearson correlation. Comprehensive ablation studies further confirm the complementary benefits of EMA, the text‐enhanced Transformer, and sentiment‐intensity contrastive learning. These results indicate that combining text‐driven deep interaction, non‐text modality enhancement via channel attention, and contrastive learning can improve the accuracy and robustness of multimodal sentiment analysis.

The wide application of smart devices enables the availability of multimodal data, which can be utilized in many tasks. In the field of multimodal sentiment analysis, most previous works focus on exploring intra- and inter-modal interactions. However, training a network with cross-modal information (language, audio and visual) is still challenging due to the modality gap. Besides, while learning dynamics within each sample draws great attention, the learning of inter-sample and inter-class relationships is neglected. Moreover, the size of datasets limits the generalization ability of the models. To address the afore-mentioned issues, we propose a novel framework HyCon for hybrid contrastive learning of tri-modal representation. Specifically, we simultaneously perform intra-/inter-modal contrastive learning and semi-contrastive learning, with which the model can fully explore cross-modal interactions, learn inter-sample and inter-class relationships, and reduce the modality gap. Besides, refinement term and modality margin are introduced to enable a better learning of unimodal pairs. Moreover, we devise pair selection mechanism to identify and assign weights to the informative negative and positive pairs. HyCon can naturally generate many training pairs for better generalization and reduce the negative effect of limited datasets. Extensive experiments demonstrate that our method outperforms baselines on multimodal sentiment analysis and emotion recognition.