Enhanced heterogeneous graph convolutional networks with dual-level attention for aspect-based sentiment analysis
Bibliographic record
Abstract
Abstract Aspect-based sentiment analysis aims to analyze the sentimental tendencies of specific aspect terms in the target sentence. With the continuous development of deep learning technology, graph convolutional networks have been widely applied to sentiment analysis tasks and achieved satisfactory results. However, when constructing graph convolutional networks based on text contents, the model considers the contextual words and their interdependent relationships without distinction. Meanwhile, most models are built separately, without fully employing the information of part of speech and dependency relationships in the text dependency parsing. In response to the above issues, we design a heterogeneous graph neural networks model based on dual node-level and type-level attention mechanisms. The heterogeneous information network is embedded into graph convolutional networks for considering the attribute characteristics of different node types. The dual-level attention mechanism can capture both the importance between diverse adjacent nodes and the significance of different node types to the central node. The relationship between aspect terms and sentiment terms is acquired by adjusting the weights of different types of nodes. To address the issue that graph neural networks have difficulty in fully utilizing dependency parsing information, we embedded syntactic and semantic dependency enhancement. By introducing the dependency tree and the dependency parsing into the graph convolutional networks architecture, it can comprehensively model the syntax relationship and analyze the sentence structure, thereby distinguishing the important contextual information. The experimental results on multiple public datasets indicate the effectiveness of the proposed model in aspect-based sentiment analysis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".