Results 81 to 90 of about 16,304 (224)

Classifier Performance on Long‐Tail Distributions

Statistical Analysis and Data Mining: An ASA Data Science Journal, Volume 18, Issue 4, August 2025.
ABSTRACT This paper introduces a Gaussian mixture model designed to explore the implications of long‐tailedness on classification performance. Our study reveals that simple under‐specified classifiers are inherently limited in reducing generalization error within this framework, a limitation overcome by well‐specified and even more complex over ...
Artur Pak, Maxat Tezekbayev, Arman Bolatov, Igor Melnykov, Kaisar Dauletbek, Zhenisbek Assylbekov   +5 more
wiley   +1 more source

Enhanced Sentiment Intensity Regression Through LoRA Fine-Tuning on Llama 3

IEEE Access
Sentiment analysis and emotion detection are critical research areas in natural language processing (NLP), offering benefits to numerous downstream tasks.
Diefan Lin, Yi Wen, Weishi Wang, Yan Su
doaj   +1 more source

Joint Extraction Method for Spatial Relations in Chinese Geological Texts

Earth and Space Science, Volume 12, Issue 8, August 2025.
Abstract Extracting spatial relations of geological entities is an important prerequisite for achieving natural language processing tasks such as geological knowledge question answering and semantic search, and is an important means to achieve structural reconstruction of unstructured geological data.
Chuan Chen, Xiuguo Liu, Weihua Hua, Xinling Zeng, Zihan Cao, Peng Li, Chunyu Qi, Yu Huang, Jiameng Chen, Wencheng Wei   +9 more
wiley   +1 more source

RPf-GCNs: reciprocal perspective driven fused GCNs for rumor detection on social media

Journal of Big Data
The earliest detection of rumors across social media is the need to the hour in present global village. User’s are seamlessly connected in an unstructured network leading to rapid flow of information.
Zafran Khan, Jeonghwan Gwak, Naima Iltaf, Witold Pedrycz, Moongu Jeon   +4 more
doaj   +1 more source

Multi-prompt Learning Based Aspect-Category Sentiment Analysis [PDF]

Jisuanji kexue yu tansuo
Aspect-category sentiment analysis (ACSA) aims to discern aspect categories in review texts and simultaneously predict their sentiment polarity. It is an important fine-grained subtask in the field of sentiment analysis.
LIU Jinhang, LI Lin, WU Renwei, LIU Jia
doaj   +1 more source

Query-Based Keyphrase Extraction from Long Documents

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Transformer-based architectures in natural language processing force input size limits that can be problematic when long documents need to be processed. This paper overcomes this issue for keyphrase extraction by chunking the long documents while keeping
Martin Dočekal, Pavel Smrž
doaj   +1 more source

AutoSense Model for Word Sense Induction

, 2018
Word sense induction (WSI), or the task of automatically discovering multiple senses or meanings of a word, has three main challenges: domain adaptability, novel sense detection, and sense granularity flexibility. While current latent variable models are
Amplayo, Reinald Kim, Hwang, Seung-won, Song, Min   +2 more
core   +1 more source

SemEval-2016 Task 12: Clinical TempEval [PDF]

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 2016
Clinical TempEval 2016 evaluated temporal information extraction systems on the clinical domain. Nine sub-tasks were included, covering problems in time expression identification, event expression identification and temporal relation identification. Participant systems were trained and evaluated on a corpus of clinical and pathology notes from the Mayo
Steven Bethard, Guergana Savova, Wei-Te Chen, Leon Derczynski, James Pustejovsky, Marc Verhagen   +5 more
openaire   +1 more source

Toxic Discourse in the Digital Battlefield: Analysing Telegram Channels During the Russia–Ukraine ‘Conflict’

Expert Systems, Volume 42, Issue 7, July 2025.
ABSTRACT Instant messenger Telegram has emerged as a favoured platform for far‐right activism, conspiracy theories, political propaganda, and misinformation, which has its own target audience. This study explores the application of multilingual pre‐trained language models to detect and measure toxicity in political content on Telegram channels.
Arsenii Tretiakov, Sergio D'Antonio‐Maceiras, Áurea Anguera de Sojo Hernández, Alejandro Martín   +3 more
wiley   +1 more source

Extracting knowledge from customer reviews: an integrated framework for digital platform analytics

International Transactions in Operational Research, Volume 32, Issue 4, Page 2061-2086, July 2025.
Abstract Online review sites play a crucial role in shaping consumer purchasing decisions, making the analysis of customer feedback essential for businesses. Given the complexity of these reviews, often including both quantitative and qualitative data, advanced analytical frameworks are necessary.
Anastasios Kyriakidis, Stelios Tsafarakis   +1 more
wiley   +1 more source