SemEval-2016 Task 6: Detecting Stance in Tweets

Mohammad, Saif M.; Kiritchenko, Svetlana; Sobhani, Parinaz; Zhu, Xiaodan; Cherry, Colin

doi:10.18653/v1/s16-1003

Cited by 620 publications

(697 citation statements)

References 25 publications

Supporting

Mentioning

585

Contrasting

Unclassified

Order By: Relevance

“…Recently, they have achieved significant improvements in various natural language processing tasks, such as Machine Translation [2,3], Question Answering [14], Sentiment Analysis [6,11,15,18], etc. However, applying deep neural networks on target-specific Stance Detection has not been successful, as their performances have, up to now, been slightly worse than traditional machine learning algorithms with manual feature engineering, such as Support Vector Machines (SVM) [8].…”

Section: Againstmentioning

confidence: 99%

“…We propose a novel attention mechanism, which extends the current attention mechanism, from the token level, to the semantic level, through a gated structure, whereby the tokens can be encoded adaptively, according to the target. We compare the models we propose based on the token-level attention mechanism and the novel semantic-level attention mechanism with several baselines, on the target-specific Stance Detection dataset for the SemEval-2016 Task 6.A [8], which is currently the most widely applied dataset on target-specific Stance Detection in tweets. The experimental results show that substantial improvements can be achieved on this task, compared with all previous neural network-based models, by inferencing conditional tweet vector representations with respect to the given targets; the neural network model with semantic-level attention also outperforms the SVM algorithm, which achieved the previous best performance in this task [8].…”

Section: Againstmentioning

confidence: 99%

“…We compare the models we propose based on the token-level attention mechanism and the novel semantic-level attention mechanism with several baselines, on the target-specific Stance Detection dataset for the SemEval-2016 Task 6.A [8], which is currently the most widely applied dataset on target-specific Stance Detection in tweets. The experimental results show that substantial improvements can be achieved on this task, compared with all previous neural network-based models, by inferencing conditional tweet vector representations with respect to the given targets; the neural network model with semantic-level attention also outperforms the SVM algorithm, which achieved the previous best performance in this task [8]. Additionally, it should be noted that our results are obtained with a minimum of supervision, with no external domain corpus collected to pre-train target-specific word embeddings, and no extra sentiment information annotated.…”

Section: Againstmentioning

confidence: 99%

“…As said, we evaluated the effectiveness of the proposed models on the benchmark Stance Detection dataset for the SemEval-2016 Task 6.A [8]. We used the exact same data as provided to the contestants for this task, with no extra labelled data [4] or domain corpus [1,9] employed.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Besides typical tweets characteristics, such as being short and noisy, the main challenge in this task is that the decision made by the classifier has to be target-specific, whilst having very little contextual information or supervision provided. Example training data from the benchmark targetspecific Stance Detection dataset for SemEval-2016 Task 6 [8] can be found in Table 1. Deep neural networks enable the continuous vector representations of Table 1: Examples of target-specific stance detection.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Connecting Targets to Tweets: Semantic Attention-Based Model for Target-Specific Stance Detection

Zhou

Cristea

Shi

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Copies of full items can be used for personal research or study, educational, or not-for profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. Publisher's statement:"The final publication is available at Springer via https://doi.org/10.1007/978-3-319-68783-4_2 " A note on versions:The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP url' above for details on accessing the published version and note that access may require a subscription. Abstract. Understanding what people say and really mean in tweets is still a wide open research question. In particular, understanding the stance of a tweet, which is determined not only by its content, but also by the given target, is a very recent research aim of the community. It still remains a challenge to construct a tweet's vector representation with respect to the target, especially when the target is only implicitly mentioned, or not mentioned at all in the tweet. We believe that better performance can be obtained by incorporating the information of the target into the tweet's vector representation. In this paper, we thus propose to embed a novel attention mechanism at the semantic level in the bi-directional GRU-CNN structure, which is more fine-grained than the existing token-level attention mechanism. This novel attention mechanism allows the model to automatically attend to useful semantic features of informative tokens in deciding the target-specific stance, which further results in a conditional vector representation of the tweet, with respect to the given target. We evaluate our proposed model on a recent, widely applied benchmark Stance Detection dataset from Twitter for the SemEval-2016 Task 6.A. Experimental results demonstrate that the proposed model substantially outperforms several strong baselines, which include the state-of-the-art token-level attention mechanism on bi-directional GRU outputs and the SVM classifier.

show abstract

Section: Againstmentioning

confidence: 99%

Section: Againstmentioning

confidence: 99%

Section: Againstmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Connecting Targets to Tweets: Semantic Attention-Based Model for Target-Specific Stance Detection

Zhou

Cristea

Shi

2017

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

Neural network approaches for rumor stance detection: Simulating complex rumor propagation systems

Li,

Yang,

Wang

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThis research introduces a comprehensive suite of neural network models designed to tackle the challenging task of rumor stance detection within the framework of simulating complex rumor propagation systems. Our objective centers on accurately modeling the intricate structures of rumor dialogues and propagation patterns to identify user stances—whether they are in support, denial, questioning, or commenting on rumors. Unlike conventional methods that rely on simplistic keyword targeting and fail in the nuanced context of social networks, our models delve into the complexities of dialogue and propagation structures, offering a more precise and insightful analysis of rumor dynamics. In addressing the simulation and modeling of complex systems, our approach specifically focuses on the elaborate interaction networks that underpin rumor spread and reception. While our methodology does not directly engage with brain‐like computing paradigms, it reflects a similar level of sophistication in handling layered and complex information flows, analogous to cognitive processes in understanding and interpreting human communications. Employing a hierarchical attention mechanism, our models adeptly parse through multitiered dialogue sequences, effectively distinguishing between various indicators of user stances. This allows for a nuanced and detailed representation of the rumor ecosystem, significantly enhancing the accuracy of stance detection. Through rigorous testing on diverse datasets, our approach has demonstrated superior performance over existing models, thereby establishing a new benchmark in the field.

show abstract

Wisdom of crowds and commodity pricing

Fan

Binnewies

SILVA

2023

Journal of Futures Markets

View full text Add to dashboard Cite

We extract commodity‐level sentiment from the Twittersphere in 2009–2020. A long–short strategy based on sentiment shifts more than doubles the Sharpe ratio of extant commodity factors. Commodities with lower (higher) sentiment shifts tend to be overvalued (undervalued) when the aggregate market is in backwardation (contango). The sentiment premium is more pronounced during periods of macro contraction and deteriorating funding liquidity. While the premium concentrates in commodities with higher tweet intensity, sentiment extracted from influential tweets (i.e., high number of retweets/likes) does not exhibit stronger predictive ability than low‐attention tweets. Consistent with the overreaction hypothesis, the sentiment premium fully reverses 3 years postformation.

show abstract

SemEval-2016 Task 6: Detecting Stance in Tweets

Cited by 620 publications

References 25 publications

Connecting Targets to Tweets: Semantic Attention-Based Model for Target-Specific Stance Detection

Connecting Targets to Tweets: Semantic Attention-Based Model for Target-Specific Stance Detection

Neural network approaches for rumor stance detection: Simulating complex rumor propagation systems

Wisdom of crowds and commodity pricing

Contact Info

Product

Resources

About