Browse State-of-the-Art › Aspect-Based Sentiment Analysis (ABSA)

Aspect-Based Sentiment Analysis (ABSA)

185 papers with code · 18 benchmarks · 20 datasets archive 2025-07-28

Natural Language Processing

Aspect-Based Sentiment Analysis (ABSA) is a Natural Language Processing task that aims to identify and extract the sentiment of specific aspects or components of a product or service. ABSA typically involves a multi-step process that begins with identifying the aspects or features of the product or service that are being discussed in the text. This is followed by sentiment analysis, where the sentiment polarity (positive, negative, or neutral) is assigned to each aspect based on the context of the sentence or document. Finally, the results are aggregated to provide an overall sentiment for each aspect.

And recent works propose more challenging ABSA tasks to predict sentiment triplets or quadruplets (Chen et al., 2022), the most influential of which are ASTE (Peng et al., 2020; Zhai et al., 2022), TASD (Wan et al., 2020), ASQP (Zhang et al., 2021a) and ACOS with an emphasis on the implicit aspects or opinions (Cai et al., 2020a).

( Source: MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

18 leaderboard tables shown for this task, 18 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 18 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): Lap14 (1 judged, 1 placed), Rest14 (1 judged, 0 placed), Rest15 (1 judged, 1 placed), Rest16 (1 judged, 1 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
SemEval-2014 Task-4 (48 rows) MT-ISA Multi-Task Learning with LLMs for Implicit Sentiment Analysis:... — — Compare
ASTE (13 rows) MvP (multi-task) MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction code — Compare
ASQP (12 rows) MvP (multi-task) MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction code — Compare
TASD (11 rows) MvP (multi-task) MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction code — Compare
SemEval 2014 Task 4 Subtask 1+2 (10 rows) gpt-3.5 finetuned Large language models for aspect-based sentiment analysis code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
ACOS (9 rows) MvP MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction code — Compare
SemEval 2014 Task 4 Laptop (9 rows) InstructABSA InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis code — Compare
MAMS (5 rows) YORO You Only Read Once: Constituency-Oriented Relational Graph... code — Compare
Sentihood (5 rows) BERT-pair-QA-B Utilizing BERT for Aspect-Based Sentiment Analysis via... code Syntology official (archive's flag): 8 ran · 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified Compare
FABSA (4 rows) DeBERTa-pair-large FABSA: An aspect-based sentiment analysis dataset of user reviews code — Compare
SemEval 2014 Task 4 Sub Task 1 (4 rows) InstructABSA InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis code — Compare
SemEval 2015 Task 12 (2 rows) MaskedABSA Masking The Bias : From Echo Chambers to Large Scale Aspect-Based... code — Compare
SemEval 2014 Task 4 Subtask 4 (2 rows) BERT-pair-QA-B Utilizing BERT for Aspect-Based Sentiment Analysis via... code Syntology official (archive's flag): 8 ran · 19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified Compare
Lap14 (1 row) HGCN Learn from Structural Scope: Improving Aspect-Level Sentiment... code — Compare
Rest14 (1 row) HGCN Learn from Structural Scope: Improving Aspect-Level Sentiment... code — Compare
Rest15 (1 row) HGCN Learn from Structural Scope: Improving Aspect-Level Sentiment... code — Compare
Rest16 (1 row) HGCN Learn from Structural Scope: Improving Aspect-Level Sentiment... code — Compare
SemEval 2015 Task 12 (1 row) HAABSA++ A Hybrid Approach for Aspect-Based Sentiment Analysis Using Deep... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

20 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

8 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 469 · with a code link: 185 · where Syntology ran a sample: 15 (13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (15 of 469 tagged: 13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 469, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 13 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections