Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews
Named Entity Recognition (NER) is crucial for extracting entities from unstructured text, offering significant insights for businesses through customer review analysis. This study fills a gap in recognizing dish names from customer reviews, as existing literature mainly addresses food entity recogni...
Saved in:
| Main Author: | |
|---|---|
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://bspace.buid.ac.ae/handle/1234/2651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1862980615696023552 |
|---|---|
| author | ABOKHASHAN, DEENA YOUNIS |
| author_facet | ABOKHASHAN, DEENA YOUNIS |
| author_role | author |
| dc.contributor.none.fl_str_mv | Professor Sherief Abdallah |
| dc.creator.none.fl_str_mv | ABOKHASHAN, DEENA YOUNIS |
| dc.date.none.fl_str_mv | 2024-07-22T07:56:38Z 2024-07-22T07:56:38Z 2024-02 |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | 2016146139 https://bspace.buid.ac.ae/handle/1234/2651 |
| dc.language.none.fl_str_mv | en |
| dc.publisher.none.fl_str_mv | The British University in Dubai (BUiD) |
| dc.subject.none.fl_str_mv | deep learning, consumer reviews, Named Entity Recognition (NER) |
| dc.title.none.fl_str_mv | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| dc.type.none.fl_str_mv | Thesis |
| description | Named Entity Recognition (NER) is crucial for extracting entities from unstructured text, offering significant insights for businesses through customer review analysis. This study fills a gap in recognizing dish names from customer reviews, as existing literature mainly addresses food entity recognition in recipe datasets and lacks annotated datasets for this specific NER task. Domain adaptation and deep learning approaches like BiGRUs and CNNs remain underexplored. The research proposes a deep learning NER framework to accurately identify dish names in customer reviews with efficient computational resource use. In addition to the existing dataset, MenuNER dataset, an annotated dataset, ReviewsDB, was created from Yelp reviews for evaluation. Initial experiments revealed a notable performance drop in domain adaptation from food names in recipe datasets to dish names in reviews, with the F1-score nearly 50% lower. A comparative analysis of 53 deep learning models using various word embeddings, including Glove, Word2Vec, and Bert variants, showed that a simple architecture with a single-layer Bidirectional Gated Recurrent Unit (BiGRU) and Conditional Random Field (CRF) layer achieved the best performance, with an F1-score of 93.07% using glove-twitter-100 embeddings in the MenuNER dataset. Additionally, a two-layer BiGRU with a CNN and CRF achieved an F1-score of 82.40% on the ReviewsDB dataset. The study attributes performance differences to variability in annotation lengths and the broader range of terms in ReviewsDB. In conclusion, the proposed NER framework, leveraging pre-trained embeddings, provides a valuable tool for the food industry to analyze customer feedback and enhance customer satisfaction. |
| id | budr_e6340e5417b9fae37c08dbd61d8b9ed4 |
| identifier_str_mv | 2016146139 |
| language_invalid_str_mv | en |
| network_acronym_str | budr |
| network_name_str | The British University in Dubai repository |
| oai_identifier_str | oai:bspace.buid.ac.ae:1234/2651 |
| publishDate | 2024 |
| publisher.none.fl_str_mv | The British University in Dubai (BUiD) |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer ReviewsABOKHASHAN, DEENA YOUNISdeep learning, consumer reviews, Named Entity Recognition (NER)Named Entity Recognition (NER) is crucial for extracting entities from unstructured text, offering significant insights for businesses through customer review analysis. This study fills a gap in recognizing dish names from customer reviews, as existing literature mainly addresses food entity recognition in recipe datasets and lacks annotated datasets for this specific NER task. Domain adaptation and deep learning approaches like BiGRUs and CNNs remain underexplored. The research proposes a deep learning NER framework to accurately identify dish names in customer reviews with efficient computational resource use. In addition to the existing dataset, MenuNER dataset, an annotated dataset, ReviewsDB, was created from Yelp reviews for evaluation. Initial experiments revealed a notable performance drop in domain adaptation from food names in recipe datasets to dish names in reviews, with the F1-score nearly 50% lower. A comparative analysis of 53 deep learning models using various word embeddings, including Glove, Word2Vec, and Bert variants, showed that a simple architecture with a single-layer Bidirectional Gated Recurrent Unit (BiGRU) and Conditional Random Field (CRF) layer achieved the best performance, with an F1-score of 93.07% using glove-twitter-100 embeddings in the MenuNER dataset. Additionally, a two-layer BiGRU with a CNN and CRF achieved an F1-score of 82.40% on the ReviewsDB dataset. The study attributes performance differences to variability in annotation lengths and the broader range of terms in ReviewsDB. In conclusion, the proposed NER framework, leveraging pre-trained embeddings, provides a valuable tool for the food industry to analyze customer feedback and enhance customer satisfaction.The British University in Dubai (BUiD)Professor Sherief Abdallah2024-07-22T07:56:38Z2024-07-22T07:56:38Z2024-02Thesisapplication/pdf2016146139https://bspace.buid.ac.ae/handle/1234/2651enoai:bspace.buid.ac.ae:1234/26512024-07-22T23:00:42Z |
| spellingShingle | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews ABOKHASHAN, DEENA YOUNIS deep learning, consumer reviews, Named Entity Recognition (NER) |
| title | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| title_full | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| title_fullStr | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| title_full_unstemmed | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| title_short | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| title_sort | Leveraging Deep Learning and Word Embeddings to Detect Dish Names in Consumer Reviews |
| topic | deep learning, consumer reviews, Named Entity Recognition (NER) |
| url | https://bspace.buid.ac.ae/handle/1234/2651 |