Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
School of Computing and Information Systems, Singapore Management University（新加坡管理学院）；Research and Development, Mastercard（麦star公司）
Donghao Huang, Zhaoxia Wang
备注：
12 pages, 1 figure, 3 tables. Accepted at PAKDD 2026
发表信息：
In: Wong, R.CW., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2026. Lecture Notes in Computer Science(), vol 16600. Springer, Singapore
Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families--including adaptive, conditional, and reinforcement learning-based reasoning architectures--on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence--binary classification degrades up to -19.9 F1 percentage points (pp), while 27-class emotion recognition gains up to +16.0pp; (2) Distilled reasoning variants underperform base models by 3-18 pp on simpler tasks, though few-shot prompting enables partial recovery; (3) Few-shot learning improves over zero-shot in most cases regardless of model type, with gains varying by architecture and task complexity; (4) Pareto frontier analysis shows base models dominate efficiency-performance trade-offs, with reasoning justified only for complex emotion recognition despite 2.1x-54x computational overhead. We complement these quantitative findings with qualitative error analysis revealing that reasoning degrades simpler tasks through systematic over-deliberation, offering mechanistic insight beyond the high-level overthinking hypothesis.
An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses
Transitional Artificial Intelligence Research Group, School of Mathematics and Statistics, UNSW Sydney（过渡人工智能研究组，数学与统计学学院，UNSW悉尼）；Department of Civil Engineering, National Institute of Technology, Rourkela, India（土木工程系，印度国家理工学院，拉尔凯拉）；Centre for Artificial Intelligence and Innovation, Pingla Institute, Sydney, Australia（人工智能与创新中心，Pingla研究所，悉尼，澳大利亚）
Large Language Models for Sentiment Analysis to Detect Social Challenges: A Use Case with South African Languages
University of Johannesburg, South Africa（约翰内斯堡大学）；IU International University of Applied Sciences（国际应用科学大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）
A Sentiment Consolidation Framework for Meta-Review Generation
School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算与信息系统学院）；Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
College of William and Mary（威廉与玛丽学院）；University of Toronto（多伦多大学）；University Health Network（大学健康网络）；KU Leuven（鲁汶大学）；Bucknell University（巴克内尔大学）；University of Cincinnati（辛辛那提大学）；University of Alabama at Birmingham（伯明翰大学）
Fine-tuning of lightweight large language models for sentiment classification on heterogeneous financial textual data
International Business School, Zhejiang University（浙江大学国际商务学院）；Center for Data Science, Zhejiang University（浙江大学数据科学中心）；Centre for Statistics, Georg-August-Universität Göttingen（哥廷根大学统计中心）
Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales
School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；Faculty of Engineering, Graduate Faculty of Interdisciplinary Research, University of Yamanashi（山梨大学工学部）
Unveiling the Potential of Sentiment: Can Large Language Models Predict Chinese Stock Price Movements?
International Digital Economy Academy (IDEA)（国际数字经济学院（IDEA））；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Data Science and Analytics Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）数据科学与分析学域）；Financial Technology Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）金融科技学域）
Using LLMs to Establish Implicit User Sentiment of Software Desirability
Creighton University（克赖顿大学）；Dakota State University（达科他州立大学）；The Beacom College of Computer & Cyber Sciences, Dakota State University（达科他州立大学比科姆计算机与网络学院）
Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategies
Hong Kong Baptist University（香港浸会大学）；BNU-UIC Institute of AI and Future Networks（北师大-联合国际学院人工智能与未来网络研究院）；BNU-HKBU United International College（北师大-港浸大联合国际学院）；Beijing Normal University（北京师范大学）
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
University of Hong Kong（香港大学）；MPI & University of Toronto（马克斯·普朗克研究所与多伦多大学）；ETH Zürich（苏黎世联邦理工学院）；University of Michigan（密歇根大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI
Institute for Artificial Intelligence Research and Development of Serbia（塞尔维亚人工智能研究与发展研究所）；University of Belgrade, Institute for Philosophy and Social Theory, Digital Society Lab（贝尔格莱德大学哲学与社会理论研究所数字社会实验室）；Complexity Science Hub（复杂性科学中心）；University of Malta, Department of Artificial Intelligence, Faculty of Information and Communication Technology（马耳他大学信息与通信技术学院人工智能系）；University of Kragujevac, Faculty of Engineering（克拉古耶瓦茨大学工程学院）
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
Tellagence Inc.（Tellagence公司）；Villanova School of Business, Villanova University（维拉文纳大学商学院）；Maseeh College of Engineering and Computer Science, Portland State University（波特兰州立大学Maseeh工程与计算机科学学院）
