TY  - GEN
AB  - Opinion summarization and sentiment classification are key processes for understanding, analyzing, and leveraging information from customer opinions. The rapid and ceaseless increase in big data of reviews on e-commerce platforms, social media, or review portals becomes a stimulus for the automation of these processes. In recent years, deep transfer learning has opted to solve many challenging tasks in Natural Language Processing (NLP) relieving the hassles of exhaustive training and the requirement of extensive labelled datasets. In this work, we propose frameworks for Abstractive Summarization (ABS) and Sentiment Analysis (SA) of airline reviews using Pretrained Language Models (PLM). The abstractive summarization model goes through two finetuning stages, the first one, for domain adaptation and the second one, for final task learning. Several studies in the literature empirically demonstrate that review rating has a positive correlation with sentiment valence. For the sentiment classification framework, we used the rating value as a signal to determine the review sentiment, and the model is built on top of BERT (Bidirectional Encoder Representations from Transformers) architecture. We evaluated our models comprehensively with multiple metrics. Our results indicate competitive performance of the models in terms of most of the evaluation metrics.
AD  - Bina Nusantara University
AD  - Bina Nusantara University
AD  - University of Chicago
AD  - Bina Nusantara University
AU  - Ayub Syed, Ayesha
AU  - Gaol, Ford Lumban
AU  - Boediman, Alfred
AU  - Budiharto, Widodo
DA  - 2024-04-20
ID  - 11567
JF  - International Journal of Information Management Data Insights
KW  - Airline reviews
KW  - Domain adaptation
KW  - Opinion summarization
KW  - Review rating
KW  - Sentiment classification
KW  - Two-stage finetuning
L1  - https://knowledge.uchicago.edu/record/11567/files/Airline-reviews-processing.pdf
L2  - https://knowledge.uchicago.edu/record/11567/files/Airline-reviews-processing.pdf
L4  - https://knowledge.uchicago.edu/record/11567/files/Airline-reviews-processing.pdf
LA  - eng
LK  - https://knowledge.uchicago.edu/record/11567/files/Airline-reviews-processing.pdf
N2  - Opinion summarization and sentiment classification are key processes for understanding, analyzing, and leveraging information from customer opinions. The rapid and ceaseless increase in big data of reviews on e-commerce platforms, social media, or review portals becomes a stimulus for the automation of these processes. In recent years, deep transfer learning has opted to solve many challenging tasks in Natural Language Processing (NLP) relieving the hassles of exhaustive training and the requirement of extensive labelled datasets. In this work, we propose frameworks for Abstractive Summarization (ABS) and Sentiment Analysis (SA) of airline reviews using Pretrained Language Models (PLM). The abstractive summarization model goes through two finetuning stages, the first one, for domain adaptation and the second one, for final task learning. Several studies in the literature empirically demonstrate that review rating has a positive correlation with sentiment valence. For the sentiment classification framework, we used the rating value as a signal to determine the review sentiment, and the model is built on top of BERT (Bidirectional Encoder Representations from Transformers) architecture. We evaluated our models comprehensively with multiple metrics. Our results indicate competitive performance of the models in terms of most of the evaluation metrics.
PY  - 2024-04-20
T1  - Airline reviews processing: Abstractive summarization and rating-based sentiment classification using deep transfer learning
TI  - Airline reviews processing: Abstractive summarization and rating-based sentiment classification using deep transfer learning
UR  - https://knowledge.uchicago.edu/record/11567/files/Airline-reviews-processing.pdf
Y1  - 2024-04-20
ER  -