167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing
OBJECTIVES/GOALS: Our project aims to assess the composition or characteristics of research papers that score high on alternative metrics. These alternative metrics including the number of newspaper mentions, social media mentions, and the attention score as catalogued on Altmetric, a tool used to d...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2024-04-01
|
| Series: | Journal of Clinical and Translational Science |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2059866124001602/type/journal_article |
| _version_ | 1827296125688741888 |
|---|---|
| author | Alaguvalliappan Thiagarajan Christopher McCarty Edward Seh-Taylor |
| author_facet | Alaguvalliappan Thiagarajan Christopher McCarty Edward Seh-Taylor |
| author_sort | Alaguvalliappan Thiagarajan |
| collection | DOAJ |
| description | OBJECTIVES/GOALS: Our project aims to assess the composition or characteristics of research papers that score high on alternative metrics. These alternative metrics including the number of newspaper mentions, social media mentions, and the attention score as catalogued on Altmetric, a tool used to document community attention for a given research paper. METHODS/STUDY POPULATION: Our study intends to 1) Utilize topic modeling to identify prevalent themes on Altmetric, and 2) Apply network analysis to elucidate the interconnectedness among universities, funding sources, journals, and publishers associated with high-attention papers. 3) Examine how these patterns vary when attention metrics shift, such as social media mentions, newspaper mentions, or the Altmetric score. We'll first perform this analysis on all types of papers and then limit the networks to Biomedical and Clinical Sciences, and Public and Allied Health Sciences to help inform what health topics garner attention. RESULTS/ANTICIPATED RESULTS: Our initial Altmetric topic models revealed sustained attention for COVID-19 and vaccination-related publications well beyond the pandemic (specifically, papers from January 2023). Health topics like cancer, dementia, and obesity also garnered high attention. Additionally, political papers (elections, democracy), climate change, and battery research had notable attention values. Further analysis needs to be done to explain why these topics gain attention and the type of attention they garner. We will construct networks to see the relationship between attention and entities like universities, funding sources, journals, and publishers. This will identify whether certain clusters of these entities produce papers with high attention or if attention is distributed evenly amoung them. DISCUSSION/SIGNIFICANCE: To gauge the broader impact of scholarly research alternative metrics beyond citations are needed. Altmetric is used widely by CTSA’s to measure the community interest in research. Understanding the types of research that gain traction on Altmetric can help researchers understand how to garner interest from the community. |
| first_indexed | 2024-04-24T14:33:43Z |
| format | Article |
| id | doaj.art-deac1676941a4c69ab3f4922deacb6af |
| institution | Directory Open Access Journal |
| issn | 2059-8661 |
| language | English |
| last_indexed | 2024-04-24T14:33:43Z |
| publishDate | 2024-04-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Journal of Clinical and Translational Science |
| spelling | doaj.art-deac1676941a4c69ab3f4922deacb6af2024-04-03T02:00:00ZengCambridge University PressJournal of Clinical and Translational Science2059-86612024-04-018505010.1017/cts.2024.160167 An Evaluation of Altmetric Attention using Network Science and Natural Language ProcessingAlaguvalliappan Thiagarajan0Christopher McCarty1Edward Seh-Taylor2University of FloridaUniversity of FloridaUniversity of FloridaOBJECTIVES/GOALS: Our project aims to assess the composition or characteristics of research papers that score high on alternative metrics. These alternative metrics including the number of newspaper mentions, social media mentions, and the attention score as catalogued on Altmetric, a tool used to document community attention for a given research paper. METHODS/STUDY POPULATION: Our study intends to 1) Utilize topic modeling to identify prevalent themes on Altmetric, and 2) Apply network analysis to elucidate the interconnectedness among universities, funding sources, journals, and publishers associated with high-attention papers. 3) Examine how these patterns vary when attention metrics shift, such as social media mentions, newspaper mentions, or the Altmetric score. We'll first perform this analysis on all types of papers and then limit the networks to Biomedical and Clinical Sciences, and Public and Allied Health Sciences to help inform what health topics garner attention. RESULTS/ANTICIPATED RESULTS: Our initial Altmetric topic models revealed sustained attention for COVID-19 and vaccination-related publications well beyond the pandemic (specifically, papers from January 2023). Health topics like cancer, dementia, and obesity also garnered high attention. Additionally, political papers (elections, democracy), climate change, and battery research had notable attention values. Further analysis needs to be done to explain why these topics gain attention and the type of attention they garner. We will construct networks to see the relationship between attention and entities like universities, funding sources, journals, and publishers. This will identify whether certain clusters of these entities produce papers with high attention or if attention is distributed evenly amoung them. DISCUSSION/SIGNIFICANCE: To gauge the broader impact of scholarly research alternative metrics beyond citations are needed. Altmetric is used widely by CTSA’s to measure the community interest in research. Understanding the types of research that gain traction on Altmetric can help researchers understand how to garner interest from the community.https://www.cambridge.org/core/product/identifier/S2059866124001602/type/journal_article |
| spellingShingle | Alaguvalliappan Thiagarajan Christopher McCarty Edward Seh-Taylor 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing Journal of Clinical and Translational Science |
| title | 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing |
| title_full | 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing |
| title_fullStr | 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing |
| title_full_unstemmed | 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing |
| title_short | 167 An Evaluation of Altmetric Attention using Network Science and Natural Language Processing |
| title_sort | 167 an evaluation of altmetric attention using network science and natural language processing |
| url | https://www.cambridge.org/core/product/identifier/S2059866124001602/type/journal_article |
| work_keys_str_mv | AT alaguvalliappanthiagarajan 167anevaluationofaltmetricattentionusingnetworkscienceandnaturallanguageprocessing AT christophermccarty 167anevaluationofaltmetricattentionusingnetworkscienceandnaturallanguageprocessing AT edwardsehtaylor 167anevaluationofaltmetricattentionusingnetworkscienceandnaturallanguageprocessing |