Triple Dimensional Valence-Arousal-Dominance Encouraging Graph Attention Networks to Exploit Aspect-based Sentiment Analysis Article Swipe
Xuefeng Shi
,
Weiping Ding
,
Min Hu
,
Xin Kang
,
Fuji Ren
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-6617154/v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-6617154/v1
As a fine-grained sentiment analysis subtask in the Natural Language Processing (NLP) community, Aspect-based Sentiment Analysis (ABSA) aims to predict the sentiment polarity of the aspect terms according to the given sentence. In previous research, external affective knowledge has been utilized to enhance the representation of the sentiment information contained in the text, which has achieved impressive progress in ABSA task. However, it is worth noting that the external knowledge employed is usually leveraged from the single-dimensional perspective, which lacks diversified and multiple-dimensional exploration and leads to insufficient comprehension of the complex sentiment information. Thus, this paper proposes a novel ABSA network to fully exploit the sentiment features from triple dimensions, namely the Valence-Arousal-Dominance assisted Graph Attention Networks (VADGAT). Preliminarily, to obtain the task-relevant semantic representation, an aspect-oriented template is devised firstly to guide the fine-tuning of the pre-trained language model. Besides, to fully leverage the triple-dimensional sentiment, they are injected into the normal dependency graph to construct three mutually independent adjacent matrices, which are implemented by Graph Attention (GAT) to extract the relations among graph nodes, progressively.Meanwhile, to treat as the fourth dimension of human beings' sentiment, SenticNet is also leveraged to enhance the sentiment intensity of the words in the text, which are expected to highlight implicit information and support the final sentiment inference. Moreover, an intentional shadow network is devised and leveraged to reinforce the screening ability of sentiment information, which is integrated with the mainstream representation proportionally. Furthermore, to improve the effectiveness of this innovative strategy, this paper utilizes the Jensen-Shannon divergence to evaluate the similarity between the mainstream and the shadow modules and optimizes the designed VADGAT eventually. To validate the effectiveness of the proposed approach, this paper conducted extensive experiments on five publicly available datasets, and the results show that the approach outperforms the state-of-the-art methods.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-6617154/v1
- https://www.researchsquare.com/article/rs-6617154/latest.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4411007917
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4411007917Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-6617154/v1Digital Object Identifier
- Title
-
Triple Dimensional Valence-Arousal-Dominance Encouraging Graph Attention Networks to Exploit Aspect-based Sentiment AnalysisWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-02Full publication date if available
- Authors
-
Xuefeng Shi, Weiping Ding, Min Hu, Xin Kang, Fuji RenList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-6617154/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-6617154/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-6617154/latest.pdfDirect OA link when available
- Concepts
-
Exploit, Sentiment analysis, Valence (chemistry), Dominance (genetics), Arousal, Graph, Computer science, Attention network, Cognitive psychology, Psychology, Artificial intelligence, Theoretical computer science, Social psychology, Physics, Chemistry, Computer security, Biochemistry, Quantum mechanics, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4411007917 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-6617154/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-6617154/v1 |
| ids.openalex | https://openalex.org/W4411007917 |
| fwci | 0.0 |
| type | preprint |
| title | Triple Dimensional Valence-Arousal-Dominance Encouraging Graph Attention Networks to Exploit Aspect-based Sentiment Analysis |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10664 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9621999859809875 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Sentiment Analysis and Opinion Mining |
| topics[1].id | https://openalex.org/T13083 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9347000122070312 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Advanced Text Analysis Techniques |
| topics[2].id | https://openalex.org/T10064 |
| topics[2].field.id | https://openalex.org/fields/31 |
| topics[2].field.display_name | Physics and Astronomy |
| topics[2].score | 0.9182000160217285 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3109 |
| topics[2].subfield.display_name | Statistical and Nonlinear Physics |
| topics[2].display_name | Complex Network Analysis Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C165696696 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8247359991073608 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q11287 |
| concepts[0].display_name | Exploit |
| concepts[1].id | https://openalex.org/C66402592 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6827989220619202 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2271421 |
| concepts[1].display_name | Sentiment analysis |
| concepts[2].id | https://openalex.org/C168900304 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6527359485626221 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q171407 |
| concepts[2].display_name | Valence (chemistry) |
| concepts[3].id | https://openalex.org/C151913843 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5854150056838989 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3454555 |
| concepts[3].display_name | Dominance (genetics) |
| concepts[4].id | https://openalex.org/C36951298 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5429428219795227 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q379784 |
| concepts[4].display_name | Arousal |
| concepts[5].id | https://openalex.org/C132525143 |
| concepts[5].level | 2 |
| concepts[5].score | 0.48652857542037964 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[5].display_name | Graph |
| concepts[6].id | https://openalex.org/C41008148 |
| concepts[6].level | 0 |
| concepts[6].score | 0.4832195043563843 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[6].display_name | Computer science |
| concepts[7].id | https://openalex.org/C2993807640 |
| concepts[7].level | 2 |
| concepts[7].score | 0.45943397283554077 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q103709453 |
| concepts[7].display_name | Attention network |
| concepts[8].id | https://openalex.org/C180747234 |
| concepts[8].level | 1 |
| concepts[8].score | 0.43683552742004395 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[8].display_name | Cognitive psychology |
| concepts[9].id | https://openalex.org/C15744967 |
| concepts[9].level | 0 |
| concepts[9].score | 0.38225090503692627 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[9].display_name | Psychology |
| concepts[10].id | https://openalex.org/C154945302 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3154712915420532 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[10].display_name | Artificial intelligence |
| concepts[11].id | https://openalex.org/C80444323 |
| concepts[11].level | 1 |
| concepts[11].score | 0.261157751083374 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[11].display_name | Theoretical computer science |
| concepts[12].id | https://openalex.org/C77805123 |
| concepts[12].level | 1 |
| concepts[12].score | 0.19917652010917664 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q161272 |
| concepts[12].display_name | Social psychology |
| concepts[13].id | https://openalex.org/C121332964 |
| concepts[13].level | 0 |
| concepts[13].score | 0.1504858136177063 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[13].display_name | Physics |
| concepts[14].id | https://openalex.org/C185592680 |
| concepts[14].level | 0 |
| concepts[14].score | 0.13292157649993896 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[14].display_name | Chemistry |
| concepts[15].id | https://openalex.org/C38652104 |
| concepts[15].level | 1 |
| concepts[15].score | 0.12149536609649658 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[15].display_name | Computer security |
| concepts[16].id | https://openalex.org/C55493867 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[16].display_name | Biochemistry |
| concepts[17].id | https://openalex.org/C62520636 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[17].display_name | Quantum mechanics |
| concepts[18].id | https://openalex.org/C104317684 |
| concepts[18].level | 2 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[18].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/exploit |
| keywords[0].score | 0.8247359991073608 |
| keywords[0].display_name | Exploit |
| keywords[1].id | https://openalex.org/keywords/sentiment-analysis |
| keywords[1].score | 0.6827989220619202 |
| keywords[1].display_name | Sentiment analysis |
| keywords[2].id | https://openalex.org/keywords/valence |
| keywords[2].score | 0.6527359485626221 |
| keywords[2].display_name | Valence (chemistry) |
| keywords[3].id | https://openalex.org/keywords/dominance |
| keywords[3].score | 0.5854150056838989 |
| keywords[3].display_name | Dominance (genetics) |
| keywords[4].id | https://openalex.org/keywords/arousal |
| keywords[4].score | 0.5429428219795227 |
| keywords[4].display_name | Arousal |
| keywords[5].id | https://openalex.org/keywords/graph |
| keywords[5].score | 0.48652857542037964 |
| keywords[5].display_name | Graph |
| keywords[6].id | https://openalex.org/keywords/computer-science |
| keywords[6].score | 0.4832195043563843 |
| keywords[6].display_name | Computer science |
| keywords[7].id | https://openalex.org/keywords/attention-network |
| keywords[7].score | 0.45943397283554077 |
| keywords[7].display_name | Attention network |
| keywords[8].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[8].score | 0.43683552742004395 |
| keywords[8].display_name | Cognitive psychology |
| keywords[9].id | https://openalex.org/keywords/psychology |
| keywords[9].score | 0.38225090503692627 |
| keywords[9].display_name | Psychology |
| keywords[10].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[10].score | 0.3154712915420532 |
| keywords[10].display_name | Artificial intelligence |
| keywords[11].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[11].score | 0.261157751083374 |
| keywords[11].display_name | Theoretical computer science |
| keywords[12].id | https://openalex.org/keywords/social-psychology |
| keywords[12].score | 0.19917652010917664 |
| keywords[12].display_name | Social psychology |
| keywords[13].id | https://openalex.org/keywords/physics |
| keywords[13].score | 0.1504858136177063 |
| keywords[13].display_name | Physics |
| keywords[14].id | https://openalex.org/keywords/chemistry |
| keywords[14].score | 0.13292157649993896 |
| keywords[14].display_name | Chemistry |
| keywords[15].id | https://openalex.org/keywords/computer-security |
| keywords[15].score | 0.12149536609649658 |
| keywords[15].display_name | Computer security |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-6617154/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-6617154/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-6617154/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5064939131 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1514-9265 |
| authorships[0].author.display_name | Xuefeng Shi |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I199305430 |
| authorships[0].affiliations[0].raw_affiliation_string | Nantong University |
| authorships[0].institutions[0].id | https://openalex.org/I199305430 |
| authorships[0].institutions[0].ror | https://ror.org/02afcvw97 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I199305430 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Nantong University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xuefeng Shi |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Nantong University |
| authorships[1].author.id | https://openalex.org/A5069969191 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3180-7347 |
| authorships[1].author.display_name | Weiping Ding |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I199305430 |
| authorships[1].affiliations[0].raw_affiliation_string | Nantong University |
| authorships[1].institutions[0].id | https://openalex.org/I199305430 |
| authorships[1].institutions[0].ror | https://ror.org/02afcvw97 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I199305430 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Nantong University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Weiping Ding |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Nantong University |
| authorships[2].author.id | https://openalex.org/A5007849518 |
| authorships[2].author.orcid | https://orcid.org/0009-0008-2836-9084 |
| authorships[2].author.display_name | Min Hu |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I16365422 |
| authorships[2].affiliations[0].raw_affiliation_string | Hefei University of Technology |
| authorships[2].institutions[0].id | https://openalex.org/I16365422 |
| authorships[2].institutions[0].ror | https://ror.org/02czkny70 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I16365422 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Hefei University of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Min Hu |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Hefei University of Technology |
| authorships[3].author.id | https://openalex.org/A5031861539 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6024-3598 |
| authorships[3].author.display_name | Xin Kang |
| authorships[3].countries | JP |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I922474255 |
| authorships[3].affiliations[0].raw_affiliation_string | Tokushima University |
| authorships[3].institutions[0].id | https://openalex.org/I922474255 |
| authorships[3].institutions[0].ror | https://ror.org/044vy1d05 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I922474255 |
| authorships[3].institutions[0].country_code | JP |
| authorships[3].institutions[0].display_name | Tokushima University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xin Kang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Tokushima University |
| authorships[4].author.id | https://openalex.org/A5071943346 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4860-9184 |
| authorships[4].author.display_name | Fuji Ren |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I150229711 |
| authorships[4].affiliations[0].raw_affiliation_string | University of Electronic Science and Technology of China |
| authorships[4].institutions[0].id | https://openalex.org/I150229711 |
| authorships[4].institutions[0].ror | https://ror.org/04qr3zq92 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I150229711 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | University of Electronic Science and Technology of China |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Fuji Ren |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | University of Electronic Science and Technology of China |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-6617154/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Triple Dimensional Valence-Arousal-Dominance Encouraging Graph Attention Networks to Exploit Aspect-based Sentiment Analysis |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10664 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9621999859809875 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Sentiment Analysis and Opinion Mining |
| related_works | https://openalex.org/W2029072726, https://openalex.org/W91913183, https://openalex.org/W2936882366, https://openalex.org/W2736893848, https://openalex.org/W2128698257, https://openalex.org/W1544055438, https://openalex.org/W3003450285, https://openalex.org/W2013608943, https://openalex.org/W4399628019, https://openalex.org/W2085024878 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-6617154/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-6617154/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-6617154/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-6617154/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-6617154/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-6617154/v1 |
| publication_date | 2025-06-02 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 2, 99 |
| abstract_inverted_index.As | 1 |
| abstract_inverted_index.In | 33 |
| abstract_inverted_index.To | 274 |
| abstract_inverted_index.an | 127, 218 |
| abstract_inverted_index.as | 181 |
| abstract_inverted_index.by | 167 |
| abstract_inverted_index.in | 7, 51, 59, 201 |
| abstract_inverted_index.is | 64, 72, 130, 190, 222, 235 |
| abstract_inverted_index.it | 63 |
| abstract_inverted_index.of | 24, 46, 90, 137, 185, 198, 231, 247, 278 |
| abstract_inverted_index.on | 287 |
| abstract_inverted_index.to | 19, 29, 42, 87, 103, 121, 133, 143, 157, 171, 179, 193, 207, 226, 243, 257 |
| abstract_inverted_index.and | 82, 85, 211, 224, 264, 268, 292 |
| abstract_inverted_index.are | 150, 165, 205 |
| abstract_inverted_index.has | 39, 55 |
| abstract_inverted_index.the | 8, 21, 25, 30, 44, 47, 52, 68, 76, 91, 106, 113, 123, 135, 138, 146, 153, 173, 182, 195, 199, 202, 213, 228, 238, 245, 254, 259, 262, 265, 270, 276, 279, 293, 297, 300 |
| abstract_inverted_index.ABSA | 60, 101 |
| abstract_inverted_index.aims | 18 |
| abstract_inverted_index.also | 191 |
| abstract_inverted_index.been | 40 |
| abstract_inverted_index.five | 288 |
| abstract_inverted_index.from | 75, 109 |
| abstract_inverted_index.into | 152 |
| abstract_inverted_index.show | 295 |
| abstract_inverted_index.that | 67, 296 |
| abstract_inverted_index.they | 149 |
| abstract_inverted_index.this | 96, 248, 251, 282 |
| abstract_inverted_index.with | 237 |
| abstract_inverted_index.(GAT) | 170 |
| abstract_inverted_index.(NLP) | 12 |
| abstract_inverted_index.Graph | 116, 168 |
| abstract_inverted_index.Thus, | 95 |
| abstract_inverted_index.among | 175 |
| abstract_inverted_index.final | 214 |
| abstract_inverted_index.fully | 104, 144 |
| abstract_inverted_index.given | 31 |
| abstract_inverted_index.graph | 156, 176 |
| abstract_inverted_index.guide | 134 |
| abstract_inverted_index.human | 186 |
| abstract_inverted_index.lacks | 80 |
| abstract_inverted_index.leads | 86 |
| abstract_inverted_index.novel | 100 |
| abstract_inverted_index.paper | 97, 252, 283 |
| abstract_inverted_index.task. | 61 |
| abstract_inverted_index.terms | 27 |
| abstract_inverted_index.text, | 53, 203 |
| abstract_inverted_index.three | 159 |
| abstract_inverted_index.treat | 180 |
| abstract_inverted_index.which | 54, 79, 164, 204, 234 |
| abstract_inverted_index.words | 200 |
| abstract_inverted_index.worth | 65 |
| abstract_inverted_index.(ABSA) | 17 |
| abstract_inverted_index.VADGAT | 272 |
| abstract_inverted_index.aspect | 26 |
| abstract_inverted_index.fourth | 183 |
| abstract_inverted_index.model. | 141 |
| abstract_inverted_index.namely | 112 |
| abstract_inverted_index.nodes, | 177 |
| abstract_inverted_index.normal | 154 |
| abstract_inverted_index.noting | 66 |
| abstract_inverted_index.obtain | 122 |
| abstract_inverted_index.shadow | 220, 266 |
| abstract_inverted_index.triple | 110 |
| abstract_inverted_index.Natural | 9 |
| abstract_inverted_index.ability | 230 |
| abstract_inverted_index.beings' | 187 |
| abstract_inverted_index.between | 261 |
| abstract_inverted_index.complex | 92 |
| abstract_inverted_index.devised | 131, 223 |
| abstract_inverted_index.enhance | 43, 194 |
| abstract_inverted_index.exploit | 105 |
| abstract_inverted_index.extract | 172 |
| abstract_inverted_index.firstly | 132 |
| abstract_inverted_index.improve | 244 |
| abstract_inverted_index.modules | 267 |
| abstract_inverted_index.network | 102, 221 |
| abstract_inverted_index.predict | 20 |
| abstract_inverted_index.results | 294 |
| abstract_inverted_index.subtask | 6 |
| abstract_inverted_index.support | 212 |
| abstract_inverted_index.usually | 73 |
| abstract_inverted_index.Analysis | 16 |
| abstract_inverted_index.Besides, | 142 |
| abstract_inverted_index.However, | 62 |
| abstract_inverted_index.Language | 10 |
| abstract_inverted_index.Networks | 118 |
| abstract_inverted_index.achieved | 56 |
| abstract_inverted_index.adjacent | 162 |
| abstract_inverted_index.analysis | 5 |
| abstract_inverted_index.approach | 298 |
| abstract_inverted_index.assisted | 115 |
| abstract_inverted_index.designed | 271 |
| abstract_inverted_index.employed | 71 |
| abstract_inverted_index.evaluate | 258 |
| abstract_inverted_index.expected | 206 |
| abstract_inverted_index.external | 36, 69 |
| abstract_inverted_index.features | 108 |
| abstract_inverted_index.implicit | 209 |
| abstract_inverted_index.injected | 151 |
| abstract_inverted_index.language | 140 |
| abstract_inverted_index.leverage | 145 |
| abstract_inverted_index.methods. | 302 |
| abstract_inverted_index.mutually | 160 |
| abstract_inverted_index.polarity | 23 |
| abstract_inverted_index.previous | 34 |
| abstract_inverted_index.progress | 58 |
| abstract_inverted_index.proposed | 280 |
| abstract_inverted_index.proposes | 98 |
| abstract_inverted_index.publicly | 289 |
| abstract_inverted_index.semantic | 125 |
| abstract_inverted_index.template | 129 |
| abstract_inverted_index.utilized | 41 |
| abstract_inverted_index.utilizes | 253 |
| abstract_inverted_index.validate | 275 |
| abstract_inverted_index.(VADGAT). | 119 |
| abstract_inverted_index.Attention | 117, 169 |
| abstract_inverted_index.Moreover, | 217 |
| abstract_inverted_index.SenticNet | 189 |
| abstract_inverted_index.Sentiment | 15 |
| abstract_inverted_index.according | 28 |
| abstract_inverted_index.affective | 37 |
| abstract_inverted_index.approach, | 281 |
| abstract_inverted_index.available | 290 |
| abstract_inverted_index.conducted | 284 |
| abstract_inverted_index.construct | 158 |
| abstract_inverted_index.contained | 50 |
| abstract_inverted_index.datasets, | 291 |
| abstract_inverted_index.dimension | 184 |
| abstract_inverted_index.extensive | 285 |
| abstract_inverted_index.highlight | 208 |
| abstract_inverted_index.intensity | 197 |
| abstract_inverted_index.knowledge | 38, 70 |
| abstract_inverted_index.leveraged | 74, 192, 225 |
| abstract_inverted_index.matrices, | 163 |
| abstract_inverted_index.optimizes | 269 |
| abstract_inverted_index.reinforce | 227 |
| abstract_inverted_index.relations | 174 |
| abstract_inverted_index.research, | 35 |
| abstract_inverted_index.screening | 229 |
| abstract_inverted_index.sentence. | 32 |
| abstract_inverted_index.sentiment | 4, 22, 48, 93, 107, 196, 215, 232 |
| abstract_inverted_index.strategy, | 250 |
| abstract_inverted_index.Processing | 11 |
| abstract_inverted_index.community, | 13 |
| abstract_inverted_index.dependency | 155 |
| abstract_inverted_index.divergence | 256 |
| abstract_inverted_index.impressive | 57 |
| abstract_inverted_index.inference. | 216 |
| abstract_inverted_index.innovative | 249 |
| abstract_inverted_index.integrated | 236 |
| abstract_inverted_index.mainstream | 239, 263 |
| abstract_inverted_index.sentiment, | 148, 188 |
| abstract_inverted_index.similarity | 260 |
| abstract_inverted_index.dimensions, | 111 |
| abstract_inverted_index.diversified | 81 |
| abstract_inverted_index.eventually. | 273 |
| abstract_inverted_index.experiments | 286 |
| abstract_inverted_index.exploration | 84 |
| abstract_inverted_index.fine-tuning | 136 |
| abstract_inverted_index.implemented | 166 |
| abstract_inverted_index.independent | 161 |
| abstract_inverted_index.information | 49, 210 |
| abstract_inverted_index.intentional | 219 |
| abstract_inverted_index.outperforms | 299 |
| abstract_inverted_index.pre-trained | 139 |
| abstract_inverted_index.Aspect-based | 14 |
| abstract_inverted_index.Furthermore, | 242 |
| abstract_inverted_index.fine-grained | 3 |
| abstract_inverted_index.information, | 233 |
| abstract_inverted_index.information. | 94 |
| abstract_inverted_index.insufficient | 88 |
| abstract_inverted_index.perspective, | 78 |
| abstract_inverted_index.comprehension | 89 |
| abstract_inverted_index.effectiveness | 246, 277 |
| abstract_inverted_index.task-relevant | 124 |
| abstract_inverted_index.Jensen-Shannon | 255 |
| abstract_inverted_index.Preliminarily, | 120 |
| abstract_inverted_index.representation | 45, 240 |
| abstract_inverted_index.aspect-oriented | 128 |
| abstract_inverted_index.proportionally. | 241 |
| abstract_inverted_index.representation, | 126 |
| abstract_inverted_index.state-of-the-art | 301 |
| abstract_inverted_index.single-dimensional | 77 |
| abstract_inverted_index.triple-dimensional | 147 |
| abstract_inverted_index.multiple-dimensional | 83 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| abstract_inverted_index.progressively.Meanwhile, | 178 |
| abstract_inverted_index.Valence-Arousal-Dominance | 114 |
| cited_by_percentile_year | |
| countries_distinct_count | 2 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.08786423 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |