pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection

Wan, Wei; Zhang, Xiao; Liu, Xuqin; Chen, Wei; Wang, Tengjiao

doi:10.18653/v1/s16-1062

Cited by 120 publications

(100 citation statements)

References 8 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…Another study [45] follows the same line by constructing corpus that contains words that are against and in-favor each target to enrich the models. Similarly, [52] used a domain corpus related to Trump along with lexicon to construct a labeled dataset to detect stance towards Trump. Furthermore, [7] used context of the users tweets to construct author embedding and predict the stance.…”

Section: Related Workmentioning

confidence: 99%

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

Aldayel

Magdy

2019

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

To what extent user's stance towards a given topic could be inferred? Most of the studies on stance detection have focused on analysing user's posts on a given topic to predict the stance. However, the stance in social media can be inferred from a mixture of signals that might reflect user's beliefs including posts and online interactions. This paper examines various online features of users to detect their stance towards different topics. We compare multiple set of features, including on-topic content, network interactions, user's preferences, and online network connections. Our objective is to understand the online signals that can reveal the users' stance. Experimentation is applied on tweets dataset from the SemEval stance detection task, which covers five topics. Results show that stance of a user can be detected with multiple signals of user's online activity, including their posts on the topic, the network they interact with or follow, the websites they visit, and the content they like. The performance of the stance modelling using different network features are comparable with the state-of-the-art reported model that used textual content only. In addition, combining network and content features leads to the highest reported performance to date on the SemEval dataset with F-measure of 72.49%.We further present an extensive analysis to show how these different set of features can reveal stance. Our findings have distinct privacy implications, where they highlight that stance is strongly embedded in user's online social network that, in principle, individuals can be profiled from their interactions and connections even when they do not post about the topic.

show abstract

Section: Related Workmentioning

confidence: 99%

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

Aldayel

Magdy

2019

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

show abstract

“…Thus, the settings of both above researches were different from the settings of the SemEval-2016 Task 6.A. [16,19] ignored the target information while performing classification, whereas our experiments have clearly proven that the target-specific vector representation of tweets can substantially boost the performance. [9] relied on feature engineering and large domain corpus, to perform feature selection, which was hard to generalise to other targets; and the collection of domain corpus additionally added difficulty, because of the limitations of the Twitter API.…”

Section: Related Workmentioning

confidence: 79%

“…We compared the proposed models with the two best performing models in the SemEval-2016 Task 6.A: (1) MITRE [19], which trained separate Long ShortTerm Memory (LSTM) networks with a voting scheme for different targetsthe LSTM networks were pre-trained, by an auxiliary hashtag prediction task on 298,973 self-collected tweets; (2) pkudblab [16], which also trained separate CNN classifiers for different targets, with a voting scheme employed both in and out of each epoch, to improve the performance. We also compared against the SVM classifiers trained on the corresponding training datasets for the five targets, using word n-grams and character n-grams features, as reported in [8], representing the previous best performer for this task.…”

Section: Comparison Modelsmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Table III shows the comparison of our proposed system with the existing state-of-the-art system of SemEval 2016 Task 6 for the sentiment dataset. [8] used feature-based SVM, [40] used keyword rules, LitisMind relied on hashtag rules on external data, [39] utilized a combination of sentiment classifiers and rules, whereas [38] used a maximum entropy classifier with domain-specific features. Our system comfortably surpasses the existing best system at SemEval.…”

Section: Modelsmentioning

confidence: 99%

Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysis

Abhishek

Ekbal

Kawahra

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

In this paper, we propose a two-layered multi-task attention based neural network that performs sentiment analysis through emotion analysis. The proposed approach is based on Bidirectional Long Short-Term Memory and uses Distributional Thesaurus as a source of external knowledge to improve the sentiment and emotion prediction. The proposed system has two levels of attention to hierarchically build a meaningful representation. We evaluate our system on the benchmark dataset of SemEval 2016 Task 6 and also compare it with the state-of-theart systems on Stance Sentiment Emotion Corpus. Experimental results show that the proposed system improves the performance of sentiment analysis by 3.2 F-score points on SemEval 2016 Task 6 dataset. Our network also boosts the performance of emotion analysis by 5 F-score points on Stance Sentiment Emotion Corpus.

show abstract

pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection

Cited by 120 publications

References 8 publications

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

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

Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysis

Contact Info

Product

Resources

About