{"url":"/dataset/semeval-2014-task-4-sub-task-2","name":"SemEval-2014 Task-4","full_name":null,"description_markdown":"Sentiment analysis is increasingly viewed as a vital task both from an academic and a commercial standpoint. The majority of current approaches, however, attempt to detect the overall polarity of a sentence, paragraph, or text span, regardless of the entities mentioned (e.g., laptops, restaurants) and their aspects (e.g., battery, screen; food, service). By contrast, this task is concerned with aspect based sentiment analysis (ABSA), where the goal is to identify the aspects of given target entities and the sentiment expressed towards each aspect. Datasets consisting of customer reviews with human-authored annotations identifying the mentioned aspects of the target entities and the sentiment polarity of each aspect will be provided.\r\n\r\n***Subtask 2: Aspect term polarity***\r\n\r\nFor a given set of aspect terms within a sentence, determine whether the polarity of each aspect term is positive, negative, neutral or conflict (i.e., both positive and negative).\r\n\r\nFor example:\r\n\r\n“I loved their fajitas” → {fajitas: positive}\r\n“I hated their fajitas, but their salads were great” → {fajitas: negative, salads: positive}\r\n“The fajitas are their first plate” → {fajitas: neutral}\r\n“The fajitas were great to taste, but not to see” → {fajitas: conflict}","description_withheld":null,"homepage":"https://alt.qcri.org/semeval2014/task4/","introduced_date":"2014-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/semeval-2014-task-4-aspect-based-sentiment","title":"SemEval-2014 Task 4: Aspect Based Sentiment Analysis","first_author":"Maria Pontiki","url":null},"license":null,"modalities":[],"tasks":[{"name":"Aspect-Based Sentiment Analysis (ABSA)","url":"/task/aspect-based-sentiment-analysis","datasets_with_task":"/datasets/task/aspect-based-sentiment-analysis"},{"name":"Aspect Extraction","url":"/task/aspect-extraction","datasets_with_task":"/datasets/task/aspect-extraction"},{"name":"Aspect Category Detection","url":"/task/aspect-category-detection","datasets_with_task":"/datasets/task/aspect-category-detection"},{"name":"Aspect-Based Sentiment Analysis","url":"/task/aspect-based-sentiment-analysis-1","datasets_with_task":"/datasets/task/aspect-based-sentiment-analysis-1"},{"name":"Aspect-oriented  Opinion Extraction","url":"/task/aspect-oriented-opinion-extraction","datasets_with_task":"/datasets/task/aspect-oriented-opinion-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SemEval-2014 Task-4"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Charitarth/SemEval2014-Task4","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":107,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset_variant":"SemEval-2014 Task-4","rows":48,"metrics":["Mean Acc (Restaurant + Laptop)","Restaurant (Acc)","Laptop (Acc)"],"first_row_in_archive_order":{"model":"MT-ISA","paper":"/paper/multi-task-learning-with-llms-for-implicit","metrics":{"Laptop (Acc)":"85.74","Mean Acc (Restaurant + Laptop)":"89.21","Restaurant (Acc)":"92.68"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/aspect-extraction-on-semeval-2014-task-4-sub-1","task":"Aspect Extraction","dataset_variant":"SemEval-2014 Task-4","rows":6,"metrics":["Laptop (F1)","Restaurant (F1)","Mean F1 (Laptop + Restaurant)"],"first_row_in_archive_order":{"model":"InstructABSA","paper":"/paper/instructabsa-instruction-learning-for-aspect","metrics":{"Laptop (F1)":"92.30","Mean F1 (Laptop + Restaurant)":"92.53","Restaurant (F1)":"92.76"},"code_links":[{"title":"kevinscaria/instructabsa","url":"https://github.com/kevinscaria/instructabsa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/aspect-oriented-opinion-extraction-on-semeval","task":"Aspect-oriented  Opinion Extraction","dataset_variant":"SemEval-2014 Task-4","rows":5,"metrics":["Restaurant 2014 (F1)","Laptop 2014 (F1)","Restaurant 2015 (F1)","Restaurant 2016 (F1)"],"first_row_in_archive_order":{"model":"BARTABSA","paper":"/paper/a-unified-generative-framework-for-aspect","metrics":{"Laptop 2014 (F1)":"80.55","Restaurant 2014 (F1)":"85.38","Restaurant 2015 (F1)":"80.52","Restaurant 2016 (F1)":"87.92"},"code_links":[{"title":"yhcc/BARTABSA","url":"https://github.com/yhcc/BARTABSA"},{"title":"ROGERDJQ/RoBERTaABSA","url":"https://github.com/ROGERDJQ/RoBERTaABSA"},{"title":"sherlock-jerry/ssa-semeval","url":"https://github.com/sherlock-jerry/ssa-semeval"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/aspect-category-detection-on-semeval-2014-1","task":"Aspect Category Detection","dataset_variant":"SemEval-2014 Task-4","rows":1,"metrics":["Average Recall","Hit@5","MRR","NDCG"],"first_row_in_archive_order":{"model":"pxp","paper":"/paper/latent-aspect-detection-from-online","metrics":{"Average Recall":"0.72","Hit@5":"0.82","MRR":"0.66","NDCG":"0.66"},"code_links":[{"title":"MohammadForouhesh/latent-aspect-detection","url":"https://github.com/MohammadForouhesh/latent-aspect-detection"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multi-task-learning-with-llms-for-implicit","title":"Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning","date":"2024-12-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/masking-the-bias-from-echo-chambers-to-large","title":"Masking The Bias : From Echo Chambers to Large Scale Aspect-Based Sentiment Analysis","date":"2024-09-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rvisa-reasoning-and-verification-for-implicit","title":"RVISA: Reasoning and Verification for Implicit Sentiment Analysis","date":"2024-07-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/you-only-read-once-constituency-oriented","title":"You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification","date":"2024-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/instructabsa-instruction-learning-for-aspect","title":"InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis","date":"2023-02-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/latent-aspect-detection-from-online","title":"Latent Aspect Detection from Online Unsolicited Customer Reviews","date":"2022-04-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-unifying-the-label-space-for-aspect","title":"Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis","date":"2022-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/back-to-reality-leveraging-pattern-driven","title":"LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregation","date":"2021-10-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understand-me-if-you-refer-to-aspect","title":"Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network","date":"2021-08-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/aspect-based-sentiment-analysis-using-bert","title":"Aspect-based Sentiment Analysis using BERT with Disentangled Attention","date":"2021-07-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-unified-generative-framework-for-aspect","title":"A Unified Generative Framework for Aspect-Based Sentiment Analysis","date":"2021-06-08","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/does-syntax-matter-a-strong-baseline-for","title":"Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa","date":"2021-04-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-joint-training-dual-mrc-framework-for","title":"A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis","date":"2021-01-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/does-bert-understand-sentiment-leveraging","title":"Does BERT Understand Sentiment? Leveraging Comparisons Between Contextual and Non-Contextual Embeddings to Improve Aspect-Based Sentiment Models","date":"2020-11-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/introducing-syntactic-structures-into-target","title":"Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning","date":"2020-10-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-bert-performance-for-aspect-based","title":"Improving BERT Performance for Aspect-Based Sentiment Analysis","date":"2020-10-22","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/automated-concatenation-of-embeddings-for-1","title":"Automated Concatenation of Embeddings for Structured Prediction","date":"2020-10-10","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/aspect-sentiment-classification-with-aspect","title":"Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans","date":"2020-10-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/don-t-eclipse-your-arts-due-to-small","title":"Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction","date":"2020-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/exploiting-typed-syntactic-dependencies-for","title":"Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network","date":"2020-02-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-training-for-aspect-based","title":"Adversarial Training for Aspect-Based Sentiment Analysis with BERT","date":"2020-01-30","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/latent-opinions-transfer-network-for-target","title":"Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction","date":"2020-01-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-multi-task-learning-model-for-chinese","title":"A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction","date":"2019-12-17","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/parameterized-convolutional-neural-networks-1","title":"Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification","date":"2019-09-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adapt-or-get-left-behind-domain-adaptation","title":"Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification","date":"2019-08-30","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":0,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/attention-and-lexicon-regularized-lstm-for","title":"Attention and Lexicon Regularized LSTM for Aspect-based Sentiment Analysis","date":"2019-07-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/an-interactive-multi-task-learning-network","title":"An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis","date":"2019-06-17","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/modeling-sentiment-dependencies-with-graph","title":"Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification","date":"2019-06-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/progressive-self-supervised-attention","title":"Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis","date":"2019-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/target-oriented-opinion-words-extraction-with","title":"Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling","date":"2019-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bert-post-training-for-review-reading","title":"BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis","date":"2019-04-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/attentional-encoder-network-for-targeted","title":"Attentional Encoder Network for Targeted Sentiment Classification","date":"2019-02-25","rows_on_this_dataset":3,"code_links":5,"syntology":null},{"paper":"/paper/exploiting-coarse-to-fine-task-transfer-for","title":"Exploiting Coarse-to-Fine Task Transfer for Aspect-level Sentiment Classification","date":"2018-11-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-target-level-sentiment","title":"Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer","date":"2018-10-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-grained-attention-network-for-aspect","title":"Multi-grained Attention Network for Aspect-Level Sentiment Classification","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/iarm-inter-aspect-relation-modeling-with","title":"IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-attention-based-position-aware","title":"Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/effective-attention-modeling-for-aspect-level","title":"Effective Attention Modeling for Aspect-Level Sentiment Classification","date":"2018-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-position-aware-bidirectional-attention","title":"A Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis","date":"2018-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/target-sensitive-memory-networks-for-aspect","title":"Target-Sensitive Memory Networks for Aspect Sentiment Classification","date":"2018-07-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/exploiting-document-knowledge-for-aspect","title":"Exploiting Document Knowledge for Aspect-level Sentiment Classification","date":"2018-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/double-embeddings-and-cnn-based-sequence","title":"Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction","date":"2018-05-11","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transformation-networks-for-target-oriented","title":"Transformation Networks for Target-Oriented Sentiment Classification","date":"2018-05-03","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/aspect-based-sentiment-analysis-using-bitmask","title":"Aspect-Based Sentiment Analysis Using Bitmask Bidirectional Long Short Term Memory Networks","date":"2018-05-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/aspect-level-sentiment-classification-with","title":"Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks","date":"2018-04-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-latent-opinions-for-aspect-level","title":"Learning Latent Opinions for Aspect-Level Sentiment Classification","date":"2018-04-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/left-center-right-separated-neural-network","title":"Left-Center-Right Separated Neural Network for Aspect-based Sentiment Analysis with Rotatory Attention","date":"2018-02-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interactive-attention-networks-for-aspect","title":"Interactive Attention Networks for Aspect-Level Sentiment Classification","date":"2017-09-04","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/recurrent-attention-network-on-memory-for","title":"Recurrent Attention Network on Memory for Aspect Sentiment Analysis","date":"2017-09-01","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/attention-based-lstm-for-aspect-level","title":"Attention-based LSTM for Aspect-level Sentiment Classification","date":"2016-11-01","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/aspect-level-sentiment-classification-with-1","title":"Aspect Level Sentiment Classification with Deep Memory Network","date":"2016-05-28","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/effective-lstms-for-target-dependent","title":"Effective LSTMs for Target-Dependent Sentiment Classification","date":"2015-12-03","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":31,"samples_ran":8,"samples_unverified":23,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}