Table 1.
List of studies on citations intent analysis using deep learning.
Fig 1.
The architecture of the proposed methodology for in-text citation sentiment analysis for identification of important citation.
Table 2.
Details of intext-citation sentiment corpus.
Fig 2.
General architecture model (based on conventional frameworks).
The CBOW model architecture predicts the current word based on the context, and the Skip-gram model predicts surrounding words given the current word.
Fig 3.
Architecture of LSTM Model used for citation analysis.
Table 3.
Experimental settings combining different embedding, window size and classification.
Fig 4.
Accuracy of machine learning models with word embeddings across different window sizes, highlighting performance trends.
Fig 5.
Precision of machine learning models with word embeddings across different window sizes, highlighting performance variations.
Fig 6.
Accuracy of deep learning models with word embeddings across different window sizes, highlighting performance trends.
Fig 7.
Precision of deep learning models with word embeddings across different window sizes, highlighting performance variations.
Fig 8.
Accuracy of machine learning models with word embeddings across different window sizes using Dataset2, highlighting performance trends.
Fig 9.
Precision of machine learning models with word embeddings across varying window sizes, highlighting performance patterns.
Fig 10.
Accuracy of deep learning models with word embeddings across different window sizes using Dataset2, highlighting performance trends.
Fig 11.
Precision of deep learning models with word embeddings across varying window sizes, highlighting performance patterns.
Table 4.
Performance metrics of deep learning models on different window sizes.
Table 5.
Performance metrics of machine learning models across different window sizes.