More Like this

1. Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding

   https://doi.org/10.18653/v1/2020.emnlp-main.568  

   Huang, Jiaxin; Meng, Yu; Guo, Fang; Ji, Heng; Han, Jiawei (January 2020, EMNLP'20: 2020 Conf. on Empirical Methods in Natural Language Processing, Nov. 2020)

   null (Ed.)

   Aspect-based sentiment analysis of review texts is of great value for understanding user feedback in a fine-grained manner. It has in general two sub-tasks: (i) extracting aspects from each review, and (ii) classifying aspect-based reviews by sentiment polarity. In this pa-per, we propose a weakly-supervised approach for aspect-based sentiment analysis, which uses only a few keywords describing each aspect/sentiment without using any labeled examples. Existing methods are either designed only for one of the sub-tasks, neglecting the benefit of coupling both, or are based on topic models that may contain overlapping concepts. We propose to first learn sentiment, aspectjoint topic embeddings in the word embedding space by imposing regularizations to encourage topic distinctiveness, and then use neural models to generalize the word-level discriminative information by pre-training the classifiers with embedding-based predictions and self-training them on unlabeled data. Our comprehensive performance analysis shows that our method generates quality joint topics and outperforms the baselines significantly (7.4%and 5.1% F1-score gain on average for aspect and sentiment classification respectively) on benchmark datasets. 

   more » « less
2. Global Image Sentiment Transfer

   https://doi.org/10.1109/ICPR48806.2021.9413221  

   An, Jie; Chen, Tianlang; Zhang, Songyang; Luo, Jiebo (January 2021, IEEE International Conference on Pattern Recognition)

   null (Ed.)
3. Twitter Sentiment Geographical Index Dataset

   https://doi.org/10.1038/s41597-023-02572-7  

   Chai, Yuchen; Kakkar, Devika; Palacios, Juan; Zheng, Siqi (December 2023, Scientific Data)

   Promoting well-being is one of the key targets of the Sustainable Development Goals at the United Nations. Many national and city governments worldwide are incorporating Subjective Well-Being (SWB) indicators into their agenda, to complement traditional objective development and economic metrics. In this study, we introduce the Twitter Sentiment Geographical Index (TSGI), a location-specific expressed sentiment database with SWB implications, derived through deep-learning-based natural language processing techniques applied to 4.3 billion geotagged tweets worldwide since 2019. Our open-source TSGI database represents the most extensive Twitter sentiment resource to date, encompassing multilingual sentiment measurements across 164 countries at the admin-2 (county/city) level and daily frequency. Based on the TSGI database, we have created a web platform allowing researchers to access the sentiment indices of selected regions in the given time period. 

   more » « less
4. Privacy-Preserving Multimodal Sentiment Analysis

   https://doi.org/10.1109/JIOT.2025.3527864  

   Xu, Honghui; Li, Wei; Takabi, Daniel; Seo, Daehee; Cai, Zhipeng (June 2025, IEEE Internet of Things Journal)
5. Sentiment-based Candidate Selection for NMT

   Jones, Alex; Wijaya, Derry (August 2021, MT Summit)

   null (Ed.)

   The explosion of user-generated content (UGC)—e.g. social media posts and comments and and reviews—has motivated the development of NLP applications tailored to these types of informal texts. Prevalent among these applications have been sentiment analysis and machine translation (MT). Grounded in the observation that UGC features highly idiomatic and sentiment-charged language and we propose a decoder-side approach that incorporates automatic sentiment scoring into the MT candidate selection process. We train monolingual sentiment classifiers in English and Spanish and in addition to a multilingual sentiment model and by fine-tuning BERT and XLM-RoBERTa. Using n-best candidates generated by a baseline MT model with beam search and we select the candidate that minimizes the absolute difference between the sentiment score of the source sentence and that of the translation and and perform two human evaluations to assess the produced translations. Unlike previous work and we select this minimally divergent translation by considering the sentiment scores of the source sentence and translation on a continuous interval and rather than using e.g. binary classification and allowing for more fine-grained selection of translation candidates. The results of human evaluations show that and in comparison to the open-source MT baseline model on top of which our sentiment-based pipeline is built and our pipeline produces more accurate translations of colloquial and sentiment-heavy source texts. 

   more » « less