Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification
Classifying social media (SM) messages into relevant or irrelevant categories is challenging due to data sparsity, imbalance, and ambiguity. This study aims to improve Intelligent Transport Systems (ITS) by enhancing short text classification of traffic-related SM data. Deep learning methods such as...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/23/11009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850260261795004416 |
|---|---|
| author | Wasen Yahya Melhem Asad Abdi Farid Meziane |
| author_facet | Wasen Yahya Melhem Asad Abdi Farid Meziane |
| author_sort | Wasen Yahya Melhem |
| collection | DOAJ |
| description | Classifying social media (SM) messages into relevant or irrelevant categories is challenging due to data sparsity, imbalance, and ambiguity. This study aims to improve Intelligent Transport Systems (ITS) by enhancing short text classification of traffic-related SM data. Deep learning methods such as RNNs, CNNs, and BERT are effective at capturing context, but they can be computationally expensive, struggle with very short texts, and perform poorly with rare words. On the other hand, transfer learning leverages pre-trained knowledge but may be biased towards the pre-training domain. To address these challenges, we propose DLCTC, a novel system combining character-level, word-level, and context features with BiLSTM and TextCNN-based attention. By utilizing external knowledge, DLCTC ensures an accurate understanding of concepts and abbreviations in traffic-related short texts. BiLSTM captures context and term correlations; TextCNN captures local patterns. Multi-level attention focuses on important features across character, word, and concept levels. Experimental studies demonstrate DLCTC’s effectiveness over well-known short-text classification approaches based on CNN, RNN, and BERT. |
| format | Article |
| id | doaj-art-25ff875f40334f1ea8a73e476c82b8f9 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-25ff875f40334f1ea8a73e476c82b8f92025-08-20T01:55:41ZengMDPI AGApplied Sciences2076-34172024-11-0114231100910.3390/app142311009Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text ClassificationWasen Yahya Melhem0Asad Abdi1Farid Meziane2Data Science Research Centre, School of Computing, University of Derby, Derby DE22 1GB, UKData Science Research Centre, School of Computing, University of Derby, Derby DE22 1GB, UKData Science Research Centre, School of Computing, University of Derby, Derby DE22 1GB, UKClassifying social media (SM) messages into relevant or irrelevant categories is challenging due to data sparsity, imbalance, and ambiguity. This study aims to improve Intelligent Transport Systems (ITS) by enhancing short text classification of traffic-related SM data. Deep learning methods such as RNNs, CNNs, and BERT are effective at capturing context, but they can be computationally expensive, struggle with very short texts, and perform poorly with rare words. On the other hand, transfer learning leverages pre-trained knowledge but may be biased towards the pre-training domain. To address these challenges, we propose DLCTC, a novel system combining character-level, word-level, and context features with BiLSTM and TextCNN-based attention. By utilizing external knowledge, DLCTC ensures an accurate understanding of concepts and abbreviations in traffic-related short texts. BiLSTM captures context and term correlations; TextCNN captures local patterns. Multi-level attention focuses on important features across character, word, and concept levels. Experimental studies demonstrate DLCTC’s effectiveness over well-known short-text classification approaches based on CNN, RNN, and BERT.https://www.mdpi.com/2076-3417/14/23/11009short text classificationBiLSTM–TextCNN integrationmulti-level attention mechanismcharacter–word–concept embeddingstraffic-related social media analysisintelligent transport systems (ITS) |
| spellingShingle | Wasen Yahya Melhem Asad Abdi Farid Meziane Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification Applied Sciences short text classification BiLSTM–TextCNN integration multi-level attention mechanism character–word–concept embeddings traffic-related social media analysis intelligent transport systems (ITS) |
| title | Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification |
| title_full | Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification |
| title_fullStr | Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification |
| title_full_unstemmed | Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification |
| title_short | Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification |
| title_sort | deep learning classification of traffic related tweets an advanced framework using deep learning for contextual understanding and traffic related short text classification |
| topic | short text classification BiLSTM–TextCNN integration multi-level attention mechanism character–word–concept embeddings traffic-related social media analysis intelligent transport systems (ITS) |
| url | https://www.mdpi.com/2076-3417/14/23/11009 |
| work_keys_str_mv | AT wasenyahyamelhem deeplearningclassificationoftrafficrelatedtweetsanadvancedframeworkusingdeeplearningforcontextualunderstandingandtrafficrelatedshorttextclassification AT asadabdi deeplearningclassificationoftrafficrelatedtweetsanadvancedframeworkusingdeeplearningforcontextualunderstandingandtrafficrelatedshorttextclassification AT faridmeziane deeplearningclassificationoftrafficrelatedtweetsanadvancedframeworkusingdeeplearningforcontextualunderstandingandtrafficrelatedshorttextclassification |