Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations
Individuals with health anomalies often share their experiences on social media sites, such as Twitter, which yields an abundance of data on a global scale. Nowadays, social media data constitutes a leading source to build drug monitoring and surveillance systems. However, a proper assessment of suc...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Graz University of Technology
2022-12-01
|
| Series: | Journal of Universal Computer Science |
| Online Access: | https://lib.jucs.org/article/84130/download/pdf/ |
| _version_ | 1797974637044301824 |
|---|---|
| author | Jarashanth Selvarajah Ruwan Nawarathna |
| author_facet | Jarashanth Selvarajah Ruwan Nawarathna |
| author_sort | Jarashanth Selvarajah |
| collection | DOAJ |
| description | Individuals with health anomalies often share their experiences on social media sites, such as Twitter, which yields an abundance of data on a global scale. Nowadays, social media data constitutes a leading source to build drug monitoring and surveillance systems. However, a proper assessment of such data requires discarding mentions which do not express drug-related personal health experiences. We automate this process by introducing a novel deep learning model. The model includes character-level and word-level embeddings, embedding-level attention, convolu- tional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and context-aware attentions. An embedding for a word is produced by integrating both word-level and character-level embeddings using an embedding-level attention mechanism, which selects the salient features from both embeddings without expanding dimensionality. The resultant embedding is further analyzed by three CNN layers independently, where each extracts unique n-grams. BiGRUs followed by attention layers further process the outputs from each CNN layer. Besides, the resultant embedding is also encoded by a BiGRU with attention. Our model is developed to cope with the intricate attributes inherent to tweets such as vernacular texts, descriptive medical phrases, frequently misspelt words, abbreviations, short messages, and others. All these four outputs are summed and sent to a softmax classifier. We built a dataset by incorporating tweets from two benchmark datasets designed for the same objective to evaluate the performance. Our model performs substantially better than existing models, including several customized Bidirectional Encoder Representations from Transformers (BERT) models with an F1-score of 0.772. |
| first_indexed | 2024-04-11T04:22:57Z |
| format | Article |
| id | doaj.art-9a5573722f2f4d89a769f555e563702a |
| institution | Directory Open Access Journal |
| issn | 0948-6968 |
| language | English |
| last_indexed | 2024-04-11T04:22:57Z |
| publishDate | 2022-12-01 |
| publisher | Graz University of Technology |
| record_format | Article |
| series | Journal of Universal Computer Science |
| spelling | doaj.art-9a5573722f2f4d89a769f555e563702a2022-12-30T09:54:04ZengGraz University of TechnologyJournal of Universal Computer Science0948-69682022-12-0128121312132910.3897/jucs.8413084130Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context RepresentationsJarashanth Selvarajah0Ruwan Nawarathna1Postgraduate Institute of Science, University of PeradeniyaDepartment of Statistics and Computer Science, University of PeradeniyaIndividuals with health anomalies often share their experiences on social media sites, such as Twitter, which yields an abundance of data on a global scale. Nowadays, social media data constitutes a leading source to build drug monitoring and surveillance systems. However, a proper assessment of such data requires discarding mentions which do not express drug-related personal health experiences. We automate this process by introducing a novel deep learning model. The model includes character-level and word-level embeddings, embedding-level attention, convolu- tional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and context-aware attentions. An embedding for a word is produced by integrating both word-level and character-level embeddings using an embedding-level attention mechanism, which selects the salient features from both embeddings without expanding dimensionality. The resultant embedding is further analyzed by three CNN layers independently, where each extracts unique n-grams. BiGRUs followed by attention layers further process the outputs from each CNN layer. Besides, the resultant embedding is also encoded by a BiGRU with attention. Our model is developed to cope with the intricate attributes inherent to tweets such as vernacular texts, descriptive medical phrases, frequently misspelt words, abbreviations, short messages, and others. All these four outputs are summed and sent to a softmax classifier. We built a dataset by incorporating tweets from two benchmark datasets designed for the same objective to evaluate the performance. Our model performs substantially better than existing models, including several customized Bidirectional Encoder Representations from Transformers (BERT) models with an F1-score of 0.772.https://lib.jucs.org/article/84130/download/pdf/ |
| spellingShingle | Jarashanth Selvarajah Ruwan Nawarathna Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations Journal of Universal Computer Science |
| title | Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations |
| title_full | Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations |
| title_fullStr | Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations |
| title_full_unstemmed | Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations |
| title_short | Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations |
| title_sort | identifying tweets with personal medication intake mentions using attentive character and localized context representations |
| url | https://lib.jucs.org/article/84130/download/pdf/ |
| work_keys_str_mv | AT jarashanthselvarajah identifyingtweetswithpersonalmedicationintakementionsusingattentivecharacterandlocalizedcontextrepresentations AT ruwannawarathna identifyingtweetswithpersonalmedicationintakementionsusingattentivecharacterandlocalizedcontextrepresentations |