---
title: "Adaptive Recursive Neural Network for — Dong 2014"
description: "The paper addresses target-dependent sentiment classification on Twitter: given a tweet and one entity mentioned in it, the task is to decide whether the…"
authors: ["Li Dong", "Furu Wei", "Chuanqi Tan", "Duyu Tang", "Ming Zhou", "Ke Xu"]
year: 2014
venue: "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
source: "https://aclanthology.org/P14-2009/"
doi: "10.3115/v1/p14-2009"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/dong-2014-adaptive-recursive-neural-network-target/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/dong-2014-adaptive-recursive-neural-network-target/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2014](https://md.research.elamur.ai/free/en/papers/2014/) / Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification

# Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification

**Authors:** [Li Dong](https://md.research.elamur.ai/free/en/authors/li-dong/), [Furu Wei](https://md.research.elamur.ai/free/en/authors/furu-wei/), [Chuanqi Tan](https://md.research.elamur.ai/free/en/authors/chuanqi-tan/), [Duyu Tang](https://md.research.elamur.ai/free/en/authors/duyu-tang/), [Ming Zhou](https://md.research.elamur.ai/free/en/authors/ming-zhou/), Ke Xu · **Year:** 2014 · **Venue:** Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P14-2009/) · [PDF](https://aclanthology.org/P14-2009.pdf) · [DOI 10.3115/v1/p14-2009](https://doi.org/10.3115/v1/p14-2009) · [OpenAlex](https://openalex.org/W2251124635)

**Citations:** 1074 citations (openalex-snapshot · 2026-10-14) · [137](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses target-dependent sentiment classification on Twitter: given a tweet and one entity mentioned in it, the task is to decide whether the author's attitude toward that entity is positive, negative or neutral. One tweet can hold different opinions about different targets. The authors restructure each tweet's dependency parse so that the chosen target becomes the root. They then apply AdaRNN, a recursive neural network that passes sentiment from surrounding words up to the target node. Instead of a single composition matrix, AdaRNN has several. At each merge it computes a soft mixture over them, conditioned on the child vectors and the dependency relation type. The authors also release a manually labelled corpus of about 6,900 tweets. AdaRNN with dependency-type features reaches 65.8% accuracy and 65.5 macro-F1. This beats SVM baselines, including a re-implementation of the rule-based method of Jiang et al. (2011), and a plain RNN. The work shows that learned, syntax-aware composition can replace fragile hand-written rules on noisy social-media text.

## Key points
- **Dataset:**
  - Tweets were collected via Twitter API keyword queries such as "bill gates", "xbox" and "google".
  - The split is 6,248 training and 692 test tweets.
  - Classes were sampled to 25% negative, 50% neutral and 25% positive.
  - Two annotators agreed on about 82.5% of a sampled subset.
- **Pipeline:**
  - Tokenization uses the Gimpel et al. Twitter tokenizer.
  - Dependency parses come from the Stanford Parser.
  - SVM baselines use Liblinear.
  - Training minimizes cross-entropy with L2 regularization using AdaGrad.
- **Model settings:**
  - Word vectors have 25 dimensions and are updated during training.
  - The nonlinearity is tanh.
  - AdaRNN uses 10 composition matrices.
- **Results (accuracy / macro-F1):**
  - SVM-indep: 62.7 / 60.2
  - SVM-dep: 63.4 / 63.3
  - RNN: 63.0 / 62.8
  - AdaRNN-w/oE: 64.9 / 64.4
  - AdaRNN-w/E: 65.8 / 65.5
  - AdaRNN-comb (AdaRNN root vector plus uni/bi-gram features in an SVM): 66.3 / 65.9
- **Error analysis:** The hand-crafted target rules of Jiang et al. rarely fired on tweets because POS tags and parses were too noisy. This explains why SVM-dep gained little over SVM-indep.

## Interesting ideas
- **Re-root the parse tree at the query entity.** Rebuilding the tree so the target sits at the top gives a separate composition path for each entity in the same sentence. This trick could serve any entity- or aspect-level task, such as opinions about specific products or places in Ukrainian texts.
- **Mixture of composition functions instead of one.** The model learns a gated, weighted blend of several transformation matrices at each node. This is an early mixture-of-experts style design, and it lets constructions like negation or comparison get their own behaviour without anyone writing rules.
- **Feed syntactic labels only into the gate.** Dependency relation types enter as a one-hot vector that decides which composition function to use, rather than being concatenated to word vectors. This is a lightweight way to inject linguistic annotation (e.g., UD relations) into a neural model, and it stays robust when the parser makes mistakes.
- **Temperature β on the gating softmax.** A single β moves selection smoothly from uniform (β = 0) through standard softmax to hard argmax as β grows large. The best results came at β = 2, while hard selection made training unstable. Sweeping β is a cheap diagnostic for whether soft routing actually helps.
- **Balanced, target-annotated evaluation set with ablations.** The paper compares a bag-of-words SVM restricted to words connected to the target against a plain RNN on the same tree. This isolates how much of the gain comes from structure versus adaptive composition, an evaluation design worth copying when testing new architectures.

*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: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

137 papers of our library cite it (of the 140884 whose bibliographies we read); 19 of them have a page here, 118 not yet.

- [Interpreting Neural Networks to Improve Politeness Comprehension](https://md.research.elamur.ai/free/en/papers/aubakirova-2016-interpreting-neural-networks-improve-politeness/)
- [Recurrent Attention Network on Memory for Aspect Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/chen-2017-recurrent-attention-network-memory-aspect/)
- [Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew](https://md.research.elamur.ai/free/en/papers/coling-2018-amram-representations-architectures-neural-sentiment-analysis/)
- [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/he-2019-interactive-multi-task-learning-network/)
- [A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/jiang-2019-challenge-dataset-effective-models-aspect/)
- [HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition](https://md.research.elamur.ai/free/en/papers/langstream-2021-chriqui-hebert-hebemo-hebrew-bert-model/)
- [Transformation Networks for Target-Oriented Sentiment Classification](https://md.research.elamur.ai/free/en/papers/li-2018-transformation-networks-target-oriented-sentiment/)
- [Arabic aspect based sentiment analysis using bidirectional GRU based models](https://md.research.elamur.ai/free/en/papers/m-2021-abdelgwad-arabic-aspect-based-sentiment-analysis/)
- [Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network](https://md.research.elamur.ai/free/en/papers/mishra-2017-learning-cognitive-features-gaze-data/)
- [Metaphor as a Medium for Emotion: An Empirical Study](https://md.research.elamur.ai/free/en/papers/mohammad-2016-metaphor-as-medium-emotion-empirical/)
- [Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree](https://md.research.elamur.ai/free/en/papers/sun-2019-aspect-level-sentiment-analysis-convolution/)
- [Aspect Level Sentiment Classification with Deep Memory Network](https://md.research.elamur.ai/free/en/papers/tang-2016-aspect-level-sentiment-classification-deep/)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://md.research.elamur.ai/free/en/papers/tang-2016-effective-lstms-target-dependent-sentiment/)
- [Attention-based LSTM for Aspect-level Sentiment Classification](https://md.research.elamur.ai/free/en/papers/wang-2016-attention-based-lstm-aspect-level/)
- [Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2016-recursive-neural-conditional-random-fields/)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/wang-2020-relational-graph-attention-network-aspect/)
- [pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection](https://md.research.elamur.ai/free/en/papers/wei-2016-pkudblab-semeval-2016-task-6/)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://md.research.elamur.ai/free/en/papers/xu-2020-position-aware-tagging-aspect-sentiment/)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://md.research.elamur.ai/free/en/papers/zhang-2019-aspect-based-sentiment-classification-aspect/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{dong2014adaptive,
  title = {{Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification}},
  author = {Dong, Li and Wei, Furu and Tan, Chuanqi and Tang, Duyu and Zhou, Ming and Xu, Ke},
  booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2014},
  doi = {10.3115/v1/p14-2009},
  url = {https://doi.org/10.3115/v1/p14-2009}
}
```

- [← previous A* CCG Parsing with a Supertag-factored Model](https://md.research.elamur.ai/free/en/papers/aclbulk-2014-lewis-ccg-parsing-supertag-factored-model/)
- [next → Aligning English Strings with Abstract Meaning Representation Graphs](https://md.research.elamur.ai/free/en/papers/pourdamghani-2014-aligning-english-strings-abstract-meaning/)
- [↑ back to papers of 2014](https://md.research.elamur.ai/free/en/papers/2014/)

## References

17 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yoshua Bengio, Réjean Ducharme, Pascal Vincent, and Christian Janvin. 2003. A neural probabilistic language model. JMLR, 3:1137–1155, March. [find](https://scholar.google.com/scholar?q=Yoshua+Bengio%2C+Re%CC%81jean+Ducharme%2C+Pascal+Vincent%2C+and+Christian+Janvin%2E+2003%2E+A+neural+probabilistic+language+model%2E+JMLR%2C+3%3A1137%E2%80%931155%2C+March%2E)
2. Li Dong, Furu Wei, Ming Zhou, and Ke Xu. 2014. Adaptive multi-compositionality for recursive neural models with applications to sentiment analysis. In Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI). AAAI. [find](https://scholar.google.com/scholar?q=Li+Dong%2C+Furu+Wei%2C+Ming+Zhou%2C+and+Ke+Xu%2E+2014%2E+Adaptive+multi%2Dcompositionality+for+recursive+neural+models+with+applications+to+sentiment+analysis%2E+In+Twenty%2DEighth+AAAI+Conference+on+Artificial+Intel)
3. John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. JMLR, 12:2121–2159, July. [find](https://scholar.google.com/scholar?q=John+Duchi%2C+Elad+Hazan%2C+and+Yoram+Singer%2E+2011%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+JMLR%2C+12%3A2121%E2%80%932159%2C+July%2E)
4. Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. Liblinear: A library for large linear classification. J. Mach. Learn. Res., 9:1871–1874, June. [find](https://scholar.google.com/scholar?q=Rong%2DEn+Fan%2C+Kai%2DWei+Chang%2C+Cho%2DJui+Hsieh%2C+Xiang%2DRui+Wang%2C+and+Chih%2DJen+Lin%2E+2008%2E+Liblinear%3A+A+library+for+large+linear+classification%2E+J%2E+Mach%2E+Learn%2E+Res%2E%2C+9%3A1871%E2%80%931874%2C+June%2E)
5. H.O. Georgii. 2011. Gibbs Measures and Phase Transitions. De Gruyter studies in mathematics. De Gruyter. [find](https://scholar.google.com/scholar?q=H%2EO%2E+Georgii%2E+2011%2E+Gibbs+Measures+and+Phase+Transitions%2E+De+Gruyter+studies+in+mathematics%2E+De+Gruyter%2E)
6. Kevin Gimpel, Nathan Schneider, Brendan O’Connor, Dipanjan Das, Daniel Mills, Jacob Eisenstein, Michael Heilman, Dani Yogatama, Jeffrey Flanigan, and Noah A. Smith. 2011. Part-of-speech tagging for twitter: Annotation, features, and experiments. In Proceedings of the 49th Annual Meeting of the Assoc… [find](https://scholar.google.com/scholar?q=Kevin+Gimpel%2C+Nathan+Schneider%2C+Brendan+O%E2%80%99Connor%2C+Dipanjan+Das%2C+Daniel+Mills%2C+Jacob+Eisenstein%2C+Michael+Heilman%2C+Dani+Yogatama%2C+Jeffrey+Flanigan%2C+and+Noah+A%2E+Smith%2E+2011%2E+Part%2Dof%2Dspeech+tagging+for+tw) [our card](https://md.research.elamur.ai/free/en/papers/gimpel-2011-part-speech-tagging-twitter-annotation/)
7. Geoffrey E. Hinton. 1986. Learning distributed representations of concepts. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, pages 1–12. Hillsdale, NJ: Erlbaum. [find](https://scholar.google.com/scholar?q=Geoffrey+E%2E+Hinton%2E+1986%2E+Learning+distributed+representations+of+concepts%2E+In+Proceedings+of+the+Eighth+Annual+Conference+of+the+Cognitive+Science+Society%2C+pages+1%E2%80%9312%2E+Hillsdale%2C+NJ%3A+Erlbaum%2E)
8. Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’04, pages 168–177, New York, NY, USA. ACM. [find](https://scholar.google.com/scholar?q=Minqing+Hu+and+Bing+Liu%2E+2004%2E+Mining+and+summarizing+customer+reviews%2E+In+Proceedings+of+the+Tenth+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+KDD+%E2%80%9904%2C+pages+168%E2%80%93177%2C+)
9. Long Jiang, Mo Yu, Ming Zhou, Xiaohua Liu, and Tiejun Zhao. 2011. Target-dependent twitter sentiment classification. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1, HLT ’11, pages 151–160, Stroudsburg, PA, USA. Assoc… [find](https://scholar.google.com/scholar?q=Long+Jiang%2C+Mo+Yu%2C+Ming+Zhou%2C+Xiaohua+Liu%2C+and+Tiejun+Zhao%2E+2011%2E+Target%2Ddependent+twitter+sentiment+classification%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Ling)
10. Dan Klein and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1, ACL ’03, pages 423– 430, Stroudsburg, PA, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dan+Klein+and+Christopher+D%2E+Manning%2E+2003%2E+Accurate+unlexicalized+parsing%2E+In+Proceedings+of+the+41st+Annual+Meeting+on+Association+for+Computational+Linguistics+%2D+Volume+1%2C+ACL+%E2%80%9903%2C+pages+423%E2%80%93+430%2C+) [our card](https://md.research.elamur.ai/free/en/papers/aclbulk-2003-klein-accurate-unlexicalized-parsing/)
11. Tetsuji Nakagawa, Kentaro Inui, and Sadao Kurohashi. 2010. Dependency tree-based sentiment classification using crfs with hidden variables. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 786–794. Associ… [find](https://scholar.google.com/scholar?q=Tetsuji+Nakagawa%2C+Kentaro+Inui%2C+and+Sadao+Kurohashi%2E+2010%2E+Dependency+tree%2Dbased+sentiment+classification+using+crfs+with+hidden+variables%2E+In+Human+Language+Technologies%3A+The+2010+Annual+Conference+o)
12. Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. 2002. Thumbs up?: sentiment classification using machine learning techniques. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, pages 79–86. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Bo+Pang%2C+Lillian+Lee%2C+and+Shivakumar+Vaithyanathan%2E+2002%2E+Thumbs+up%3F%3A+sentiment+classification+using+machine+learning+techniques%2E+In+Proceedings+of+the+ACL%2D02+conference+on+Empirical+methods+in+natura) [our card](https://md.research.elamur.ai/free/en/papers/pang-2002-thumbs-up-sentiment-classification-machine/)
13. D.E. Rumelhart, G.E. Hinton, and R.J. Williams. 1986. Learning representations by back-propagating errors. Nature, 323(6088):533–536. [find](https://scholar.google.com/scholar?q=D%2EE%2E+Rumelhart%2C+G%2EE%2E+Hinton%2C+and+R%2EJ%2E+Williams%2E+1986%2E+Learning+representations+by+back%2Dpropagating+errors%2E+Nature%2C+323%286088%29%3A533%E2%80%93536%2E)
14. Richard Socher, Cliff C. Lin, Andrew Y. Ng, and Christopher D. Manning. 2011. Parsing Natural Scenes and Natural Language with Recursive Neural Networks. In ICML. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Cliff+C%2E+Lin%2C+Andrew+Y%2E+Ng%2C+and+Christopher+D%2E+Manning%2E+2011%2E+Parsing+Natural+Scenes+and+Natural+Language+with+Recursive+Neural+Networks%2E+In+ICML%2E)
15. Richard Socher, Brody Huval, Christopher D. Manning, and Andrew Y. Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In EMNLP-CoNLL, pages 1201–1211. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Brody+Huval%2C+Christopher+D%2E+Manning%2C+and+Andrew+Y%2E+Ng%2E+2012%2E+Semantic+compositionality+through+recursive+matrix%2Dvector+spaces%2E+In+EMNLP%2DCoNLL%2C+pages+1201%E2%80%931211%2E) [our card](https://md.research.elamur.ai/free/en/papers/socher-2012-semantic-compositionality-through-recursive-matrix/)
16. Richard Socher, Alex Perelygin, Jean Y Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In EMNLP, pages 1631–1642. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Alex+Perelygin%2C+Jean+Y+Wu%2C+Jason+Chuang%2C+Christopher+D+Manning%2C+Andrew+Y+Ng%2C+and+Christopher+Potts%2E+2013%2E+Recursive+Deep+Models+for+Semantic+Compositionality+Over+a+Sentiment+Treebank%2E)
17. Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, and Manfred Stede. 2011. Lexicon-based methods for sentiment analysis. Comput. Linguist., 37(2):267–307, June. [find](https://scholar.google.com/scholar?q=Maite+Taboada%2C+Julian+Brooke%2C+Milan+Tofiloski%2C+Kimberly+Voll%2C+and+Manfred+Stede%2E+2011%2E+Lexicon%2Dbased+methods+for+sentiment+analysis%2E+Comput%2E+Linguist%2E%2C+37%282%29%3A267%E2%80%93307%2C+June%2E) [our card](https://md.research.elamur.ai/free/en/papers/taboada-2011-lexicon-based-methods-sentiment-analysis/)