Papers › IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis
IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis
Navonil Majumder, Soujanya Poria, Alex Gelbukh, er, Md. Shad Akhtar, Erik Cambria, Asif Ekbal
Sentiment analysis has immense implications in e-commerce through user feedback mining. Aspect-based sentiment analysis takes this one step further by enabling businesses to extract aspect specific sentimental information. In this paper, we present a novel approach of incorporating the neighboring aspects related information into the sentiment classification of the target aspect using memory networks. We show that our method outperforms the state of the art by 1.6{\%} on average in two distinct domains: restaurant and laptop.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Aspect-Based Sentiment Analysis (ABSA) | SemEval-2014 Task-4 | IARM | Laptop (Acc) | 73.8 | #34 of 48 | Archive leaderboard | report |
| Aspect-Based Sentiment Analysis (ABSA) | SemEval-2014 Task-4 | IARM | Mean Acc (Restaurant + Laptop) | 77.02 | #34 of 48 | Archive leaderboard | report |
| Aspect-Based Sentiment Analysis (ABSA) | SemEval-2014 Task-4 | IARM | Restaurant (Acc) | 80.0 | #34 of 48 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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