--- title: "Tweet Stance Detection Using an Attention — Siddiqua 2019" description: "The paper tackles stance detection on Twitter: deciding whether a tweet supports, opposes, or is neutral toward a given target, such as a political…" authors: ["Umme Aymun Siddiqua", "Abu Nowshed Chy", "Masaki Aono"] year: 2019 venue: "Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)" source: "https://aclanthology.org/N19-1185/" doi: "10.18653/v1/n19-1185" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/siddiqua-2019-tweet-stance-detection-attention-based/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/siddiqua-2019-tweet-stance-detection-attention-based/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2019](https://md.research.elamur.ai/free/papers/2019/page/4/) / Tweet Stance Detection Using an Attention based Neural Ensemble Model # Tweet Stance Detection Using an Attention based Neural Ensemble Model **Authors:** Umme Aymun Siddiqua, [Abu Nowshed Chy](https://md.research.elamur.ai/free/authors/abu-nowshed-chy/), Masaki Aono · **Year:** 2019 · **Venue:** Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/N19-1185/) · [PDF](https://aclanthology.org/N19-1185.pdf) · [DOI 10.18653/v1/n19-1185](https://doi.org/10.18653/v1/n19-1185) · [OpenAlex](https://openalex.org/W2946133598) **Citations:** 39 citations (openalex-snapshot · 2026-10-14) · [19](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper tackles stance detection on Twitter: deciding whether a tweet supports, opposes, or is neutral toward a given target, such as a political candidate. This is harder than sentiment analysis because the label depends on the target, and tweets are short, noisy, and full of hashtags and abbreviations. The authors propose PNEM, a neural ensemble model. The target and tweet word vectors are joined into one input matrix, and multi-kernel convolution extracts higher-level features from it. These features go to two parallel recurrent modules: a densely connected Bi-LSTM (DC-Bi-LSTM) and nested LSTMs (NLSTMs). Each module has a feed-forward attention layer that weights the important hidden states. The two outputs are concatenated and classified with softmax. PNEM was tested on the SemEval-2016 Task 6-A single-target data and on the multi-target 2016 US election dataset of Sobhani et al. (2017). On both, it beat a CNN+LSTM baseline and earlier deep learning systems. This suggests that combining newer LSTM variants with attention gives better tweet representations for target-dependent opinion mining. ## Key points - **Single-target results (SemEval-2016 Task 6-A):** The dataset has 2914 training and 1249 test tweets across 5 targets. PNEM reached F avg 72.11, compared with 67.15 for CNN+LSTM, 68.98 for SVM-ngrams, and 67.82 for MITRE (the best SemEval system). Against other deep models such as TGMN-CR, T-PAN, AS-biGRU-CNN and TAN, it gained between 1.07 and 3.44 points. - **Multi-target results:** The dataset has 4455 tweets (3119 train, 446 dev, 890 test) over three candidate pairs. PNEM improved on Seq2Seq by 3.91 points and on DMAN by 1.99 points. - **Ablation study:** Removing each component lowered F avg as follows: - multi-kernel convolution (MKC): −4.98 - NLSTMs+ATT: −4.14 - attention: −1.68 - DC-Bi-LSTM+ATT: −1.11 - target embedding: −0.99 - **Setup:** The model uses 300-d fastText skip-gram embeddings trained on Wikipedia, kernel sizes 2–5 with 600 filters, a 5-layer DC-Bi-LSTM and a 2-layer NLSTMs module. Training used Adam (learning rate 0.001), batch size 32, and up to 45 epochs. - **Preprocessing:** NLTK stop words were removed, special characters were stripped, and hashtags were segmented following Baziotis et al. (2017). *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) ## Cited by Cited by 19 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 11 not yet. - [Stance Detection in COVID-19 Tweets](https://md.research.elamur.ai/free/papers/glandt-2021-stance-detection-covid-19-tweets/) - [Infusing Knowledge from Wikipedia to Enhance Stance Detection](https://md.research.elamur.ai/free/papers/he-2022-infusing-knowledge-wikipedia-enhance-stance/) - [Knowledge Enhanced Masked Language Model for Stance Detection](https://md.research.elamur.ai/free/papers/kawintiranon-2021-knowledge-enhanced-masked-language-model/) - [Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation](https://md.research.elamur.ai/free/papers/li-2021-improving-stance-detection-multi-dataset/) - [Target-Aware Data Augmentation for Stance Detection](https://md.research.elamur.ai/free/papers/li-2021-target-aware-data-augmentation-stance/) - [Generative Data Augmentation with Contrastive Learning for Zero-Shot Stance Detection](https://md.research.elamur.ai/free/papers/li-2022-generative-data-augmentation-contrastive-learning/) - [Distilling Calibrated Knowledge for Stance Detection](https://md.research.elamur.ai/free/papers/li-2023-distilling-calibrated-knowledge-stance-detection/) - [POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection](https://md.research.elamur.ai/free/papers/liu-2022-politics-pretraining-same-story-article/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{siddiqua2019tweet, title = {{Tweet Stance Detection Using an Attention based Neural Ensemble Model}}, author = {Siddiqua, Umme Aymun and Chy, Abu Nowshed and Aono, Masaki}, booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}, year = {2019}, doi = {10.18653/v1/n19-1185}, url = {https://doi.org/10.18653/v1/n19-1185} } ``` - [← previous Tuning Multilingual Transformers for Language-Specific Named Entity Recognition](https://md.research.elamur.ai/free/papers/arkhipov-2019-tuning-multilingual-transformers-language-specific/) - [next → Tyndale STEPBible Data development for machine analysis and computational linguistics](https://md.research.elamur.ai/free/papers/hbo-2019-instone-brewer-tyndale-stepbible-data-development-machine/) - [↑ back to papers of 2019](https://md.research.elamur.ai/free/papers/2019/page/4/) ## References 3 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Target-Pair Method Overall CNN+LSTM Seq2Seq DMAN PNEM Clinton Sanders Clinton Trump Cruz Trump 46.03 43.02 47.35 47.71 54.81 56.73 58.72 54.72 56.25 57.74 56.60 60.30 60.05 53.12 53.64 58.36 [find](https://scholar.google.com/scholar?q=Target%2DPair+Method+Overall+CNN%2BLSTM+Seq2Seq+DMAN+PNEM+Clinton+Sanders+Clinton+Trump+Cruz+Trump+46%2E03+43%2E02+47%2E35+47%2E71+54%2E81+56%2E73+58%2E72+54%2E72+56%2E25+57%2E74+56%2E60+60%2E30+60%2E05+53%2E12+53%2E64+58%2E36) 2. Christos Baziotis, Nikos Pelekis, and Christos Doulk-eridis. 2017. Datastories at SemEval-2017 task 4: Deep lstm with attention for message-level and topic-based sentiment analysis. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval), pages 747–754, Vancouver, Canada.… [find](https://scholar.google.com/scholar?q=Christos+Baziotis%2C+Nikos+Pelekis%2C+and+Christos+Doulk%2Deridis%2E+2017%2E+Datastories+at+SemEval%2D2017+task+4%3A+Deep+lstm+with+attention+for+message%2Dlevel+and+topic%2Dbased+sentiment+analysis%2E+In+Proceedings+of+) 3. Kuntal Dey, Ritvik Shrivastava, and Saroj Kaushik. 2018. Topical stance detection for twitter: A two-phase lstm model using attention. In Proceedings of the 40th European Conference on Information Retrieval (ECIR), pages 529–536. Springer. \#\# Conclusion [find](https://scholar.google.com/scholar?q=Kuntal+Dey%2C+Ritvik+Shrivastava%2C+and+Saroj+Kaushik%2E+2018%2E+Topical+stance+detection+for+twitter%3A+A+two%2Dphase+lstm+model+using+attention%2E+In+Proceedings+of+the+40th+European+Conference+on+Information+Ret)