Multi-sentence and multi-intent classification using RoBERTa and graph convolutional neural network
Bibliographic record
Abstract
Abstract Citation analysis has garnered significant attention in academia, particularly in the realm of scientometrics analysis. Most studies related to citation analysis focus on quantitative aspects, assigning equal weight to every citation regardless of its placement within the paper. However, understanding the distribution of citation weight across different sections of a research article is crucial for citation analysis and impact assessment. Therefore, the analysis of citation intent becomes a pivotal task in determining the qualitative importance of a citation within a scientific article. In this context, we undertook two essential tasks related to citation analysis: citation length analysis and citation intent analysis. Through citation length analysis, we identified the optimal number of citation sentences to consider around a cited sentence. Simultaneously, citation intent analysis aimed to categorize citations into seven distinct types, namely background, motivation, uses, extends, similarities, differences, and future work. For the latter task, we introduced two novel architectures based on graph neural networks, namely CiteIntentRoBERTaGCN and CiteIntentRoBERTaGAT. The performance of these proposed models was evaluated on five multi-intent datasets curated from 1,200 research papers, considering different context lengths. The results demonstrated that the proposed models achieved state-of-the-art performance.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".