Exploring deep neural networks for multitarget stance detection

Sobhani, Parinaz; Inkpen, Diana; Zhu, Xiaodan

doi:10.1111/coin.12189

Cited by 33 publications

(38 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, MTL-LP is the best performing multilabel classification method across all the datasets. MTL-LP is also better than the best performing model Seq2Seq reported in Sobhani et al (2019) for the ETC dataset. MTL-XLD improves on the baseline models for the BBC and MFTC datasets, but performs slightly worse than MTL on the ETC dataset.…”

Section: Resultsmentioning

confidence: 83%

“…Such cases need to be formulated as Brexit Blog Corpus (Simaki et al, 2018) Utterance: rivalry between the us and china is inevitable but it needs to be kept within bounds that would preclude the use of military force. Stances: certainty, contrariety, necessity, prediction US Election Twitter Corpus (Sobhani et al, 2019) Utterance: voters mean more than super delegates @sensanders corrupt -> #hillaryclinton spends millions on msm to discourage #americans voting #sanders Stances: Clinton: AGAINST, Sanders: FAVOR Moral Foundations Twitter (Dehghani et al, 2019) Utterance: blatant racism in #colorado, #blacklivesmatter http://fb.me/1ibyxmswm Stances: cheating, harm multilabel classification (Sorower, 2010), where an instance can receive multiple, non-mutually exclusive labels. The most commonly used approaches to multiclass classification treat the task by learning models for each label.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Label Dependencies in Multilabel Stance Detection

Ferreira¹,

Vlachos

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Stance detection in social media is a wellstudied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations.

show abstract

Section: Resultsmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Incorporating Label Dependencies in Multilabel Stance Detection

Ferreira¹,

Vlachos

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…Gamalet et al [47] used ten different ML algorithms with two feature extraction algorithms that were implemented on four SA datasets (IMDB, Cornell movies, Amazon and Twitter) in a comparative analysis of their methodology. Sobhani et al [48] investigate the problem of jointly predicting the stance expressed toward multiple targets using Twitter posts. Stance detection is the task of automatically determining from the text whether the author of the text is for, against, or has a neutral view towards a proposition or target.…”

Section: Theoretical Frameworkmentioning

confidence: 99%

Opinion Mining on Social Media Data: Sentiment Analysis of User Preferences

Păvăloaia

Teodor²,

Fotache

et al. 2019

Sustainability

View full text Add to dashboard Cite

Any brand’s presence on social networks has a significant impact on emotional reactions of its users to different types of posts on social media (SM). If a company understands the preferred types of posts (photo or video) of its customers, based on their reactions, it could make use of these preferences in designing its future communication strategy. The study examines how the use of SM technology and customer-centric management systems could contribute to sustainable business development of companies by means of social customer relationship management (sCRM). The two companies included in the study provide a general consumer good in the beverage industry. As such, it may be said that users interacting with the posts these companies make on their official channels are in fact customers or potential customers. The study aims to analyze customer reaction to two types of posts (photos or videos) on six social networks: Facebook, Twitter, Instagram, Pinterest, Google+ and Youtube. It brings evidence on the differences and similarities between the SM customer behaviors of two highly competitive brands in the beverage industry. Drawing on current literature on SM, sCRM and marketing, the output of this study is the conceptualization and measurement of a brand’s SM ability to understand customer preferences for different types of posts by using various statistical tools and the sentiment analysis (SA) technique applied to big sets of data.

show abstract

“…We compared the performance of our proposed method (MKC-LSTMVs-ATT) with the state-of-the-art multi-target stance detection methods including Seq2Seq method proposed by Sobhani et al [50] and DMAN method proposed by Wei et al [23]. The comparative results are presented in Table 7.…”

Section: Comparison With Related Workmentioning

confidence: 99%

“…The comparative results are presented in Table 7. Seq2Seq [50] is the attention-based encoder-decoder deep neural network model for multi-target stance detection. The encoder converted the input text into a vector representation, and the decoder generates stance labels towards multiple targets.…”

Section: Comparison With Related Workmentioning

confidence: 99%

Tweet Stance Detection Using Multi-Kernel Convolution and Attentive LSTM Variants

Siddiqua

Chy

Aono

2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Umme Aymun SIDDIQUA †a) , Abu Nowshed CHY †b) , Nonmembers, and Masaki AONO †c) , Member SUMMARY Stance detection in twitter aims at mining user stances expressed in a tweet towards a single or multiple target entities. Detecting and analyzing user stances from massive opinion-oriented twitter posts provide enormous opportunities to journalists, governments, companies, and other organizations. Most of the prior studies have explored the traditional deep learning models, e.g., long short-term memory (LSTM) and gated recurrent unit (GRU) for detecting stance in tweets. However, compared to these traditional approaches, recently proposed densely connected bidirectional LSTM and nested LSTMs architectures effectively address the vanishinggradient and overfitting problems as well as dealing with long-term dependencies. In this paper, we propose a neural network model that adopts the strengths of these two LSTM variants to learn better long-term dependencies, where each module coupled with an attention mechanism that amplifies the contribution of important elements in the final representation. We also employ a multi-kernel convolution on top of them to extract the higherlevel tweet representations. Results of extensive experiments on single and multi-target benchmark stance detection datasets show that our proposed method achieves substantial improvement over the current state-of-the-art deep learning based methods.

show abstract

Exploring deep neural networks for multitarget stance detection

Cited by 33 publications

References 29 publications

Incorporating Label Dependencies in Multilabel Stance Detection

Incorporating Label Dependencies in Multilabel Stance Detection

Opinion Mining on Social Media Data: Sentiment Analysis of User Preferences

Tweet Stance Detection Using Multi-Kernel Convolution and Attentive LSTM Variants

Contact Info

Product

Resources

About