Understanding Emotion in Discourse: Recognition Insights and Linguistic Patterns for Generation

• URL: http://arxiv.org/abs/2601.00181v1
• Date: Thu, 01 Jan 2026 02:49:44 GMT
• Title: Understanding Emotion in Discourse: Recognition Insights and Linguistic Patterns for Generation
• Abstract summary: We conduct a rigorous ablation study with 10-seed evaluation for recognition.<n>For linguistic analysis, we analyze 5,286 discourse marker occurrences.<n>We find a significant association between emotion and marker positioning.
• Score: 0.36980845568339205
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Emotion Recognition in Conversation (ERC) has achieved high accuracy, two critical gaps remain: a limited understanding of \textit{which} architectural choices actually matter, and a lack of linguistic analysis connecting recognition to generation. We address both gaps through a systematic analysis of the IEMOCAP dataset. For recognition, we conduct a rigorous ablation study with 10-seed evaluation and report three key findings. First, conversational context is paramount, with performance saturating rapidly -- 90\% of the total gain achieved within just the most recent 10--30 preceding turns (depending on the label set). Second, hierarchical sentence representations help at utterance-level, but this benefit disappears once conversational context is provided, suggesting that context subsumes intra-utterance structure. Third, external affective lexicons (SenticNet) provide no gain, indicating that pre-trained encoders already capture necessary emotional semantics. With simple architectures using strictly causal context, we achieve 82.69\% (4-way) and 67.07\% (6-way) weighted F1, outperforming prior text-only methods including those using bidirectional context. For linguistic analysis, we analyze 5,286 discourse marker occurrences and find a significant association between emotion and marker positioning ($p < .0001$). Notably, "sad" utterances exhibit reduced left-periphery marker usage (21.9\%) compared to other emotions (28--32\%), consistent with theories linking left-periphery markers to active discourse management. This connects to our recognition finding that sadness benefits most from context (+22\%p): lacking explicit pragmatic signals, sad utterances require conversational history for disambiguation.

Related papers

• SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis [45.09009423124683]
  Speech Sentiment Analysis plays a critical role in decoding paralinguistic cues for diverse real-world applications.<n>Existing approaches rely on text-centric pipelines that cascade Automatic Speech Recognition with text analysis.<n>We propose a novel dataset, SpeechSense, for fine-grained speech sentiment analysis.
  arXiv  Detail & Related papers  (2026-08-18T15:51:27Z)
• EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis [1.5803208833562954]
  EmotionAI is a fully local Computational Intelligence pipeline that couples Speech Emotion Recognition with generative reasoning.<n>Speaker diarisation, Whisper Automatic Speech Recognition (ASR) and a wav2vec2 emotion classifier produce per-segment affective evidence.<n>The contribution is not state-of-the-art SER but an auditable, privacy-preserving integration of imperfect affective evidence into grounded conversational analysis.
  arXiv  Detail & Related papers  (2026-06-22T20:45:49Z)
• Low Resource Multimodal Translation of Nepali Spoken Words into Emotion-Conditioned Sign Language Avatars [0.0]
  NEST-V1 is a proof-of-concept framework that generates emotion-conditioned Nepali Sign Language avatars from spoken input.<n>Our preliminary results indicate the viability of real-time, emotionally expressive sign language communication systems for the hearing-impaired community.
  arXiv  Detail & Related papers  (2026-05-04T15:17:49Z)
• SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation [55.26111461168754]
  We introduce SMILE: Semantic Metric Integrating Lexical Exactness, a novel approach that combines sentence-level semantic understanding with keyword-level semantic understanding and easy keyword matching.<n>It is highly correlated with human judgments and computationally lightweight, bridging the gap between lexical and semantic evaluation.
  arXiv  Detail & Related papers  (2025-11-21T17:30:18Z)
• Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMs [2.8728982844941178]
  Speech Emotion Recognition (SER) focuses on identifying emotional states from spoken language. We propose a novel approach that first refines all available transcriptions to ensure data reliability. We then segment each complete conversation into smaller dialogues and use these dialogues as context to predict the emotion of the target utterance within the dialogue.
  arXiv  Detail & Related papers  (2024-10-27T04:23:34Z)
• Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling [50.99252242917458]
  Conversational Speech Synthesis (CSS) aims to accurately express an utterance with the appropriate prosody and emotional inflection within a conversational setting. To address the issue of data scarcity, we meticulously create emotional labels in terms of category and intensity. Our model outperforms the baseline models in understanding and rendering emotions.
  arXiv  Detail & Related papers  (2023-12-19T08:47:50Z)
• Speech and Text-Based Emotion Recognizer [0.9168634432094885]
  We build a balanced corpus from publicly available datasets for speech emotion recognition. Our best system, a multi-modal speech, and text-based model, provides a performance of UA(Unweighed Accuracy) + WA (Weighed Accuracy) of 157.57 compared to the baseline algorithm performance of 119.66.
  arXiv  Detail & Related papers  (2023-12-10T05:17:39Z)
• Multiscale Contextual Learning for Speech Emotion Recognition in Emergency Call Center Conversations [4.297070083645049]
  This paper presents a multi-scale conversational context learning approach for speech emotion recognition. We investigated this approach on both speech transcriptions and acoustic segments. According to our tests, the context derived from previous tokens has a more significant influence on accurate prediction than the following tokens.
  arXiv  Detail & Related papers  (2023-08-28T20:31:45Z)
• Distributed Marker Representation for Ambiguous Discourse Markers and Entangled Relations [50.31129784616845]
  We learn a Distributed Marker Representation (DMR) by utilizing the unlimited discourse marker data with a latent discourse sense. Our method also offers a valuable tool to understand complex ambiguity and entanglement among discourse markers and manually defined discourse relations.
  arXiv  Detail & Related papers  (2023-06-19T00:49:51Z)
• Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents [61.63208012250885]
  We formulate recognizing semantic differences as a token-level regression task. We study three unsupervised approaches that rely on a masked language model. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels.
  arXiv  Detail & Related papers  (2023-05-22T17:58:04Z)
• We're Afraid Language Models Aren't Modeling Ambiguity [136.8068419824318]
  Managing ambiguity is a key part of human language understanding. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence. We show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity.
  arXiv  Detail & Related papers  (2023-04-27T17:57:58Z)
• Feature Selection Enhancement and Feature Space Visualization for Speech-Based Emotion Recognition [2.223733768286313]
  We present speech features enhancement strategy that improves speech emotion recognition. The strategy is compared with the state-of-the-art methods used in the literature. Our method achieved an average recognition gain of 11.5% for six out of seven emotions for the EMO-DB dataset, and 13.8% for seven out of eight emotions for the RAVDESS dataset.
  arXiv  Detail & Related papers  (2022-08-19T11:29:03Z)
• Beyond Isolated Utterances: Conversational Emotion Recognition [33.52961239281893]
  Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. We propose several approaches for conversational emotion recognition (CER) by treating it as a sequence labeling task. We investigated transformer architecture for CER and, compared it with ResNet-34 and BiLSTM architectures in both contextual and context-less scenarios.
  arXiv  Detail & Related papers  (2021-09-13T16:40:35Z)
• BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis [18.1320976106637]
  The main difference between conversational sentiment analysis and single sentence sentiment analysis is the existence of context information. Existing approaches employ complicated deep learning structures to distinguish different parties in a conversation and then model the context information. We propose a fast, compact and parameter-efficient party-ignorant framework named bidirectional emotional recurrent unit for conversational sentiment analysis.
  arXiv  Detail & Related papers  (2020-05-31T11:13:13Z)
• A Deep Neural Framework for Contextual Affect Detection [51.378225388679425]
  A short and simple text carrying no emotion can represent some strong emotions when reading along with its context. We propose a Contextual Affect Detection framework which learns the inter-dependence of words in a sentence.
  arXiv  Detail & Related papers  (2020-01-28T05:03:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.