Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification

Deriu, Jan; Lucchi, Aurélien; Luca, Valéria De; Severyn, Aliaksei; Müller, Simon; Cieliebak, Mark; Hofmann, Thomas; Jäggi, Martin

doi:10.1145/3038912.3052611

Cited by 95 publications

(102 citation statements)

References 20 publications

Supporting

Mentioning

101

Contrasting

Order By: Relevance

“…In reality, however, high-quality sentiment labels are often scarce due to the labor-consuming and error-prone human annotation process [26]. To address this limitation, researchers have used sentimental hashtags and emoticons as weak sentiment labels [22,23]. These weak labels are usually language/community-specific.…”

Section: Related Workmentioning

confidence: 99%

“…As cross-lingual studies on Tweets are very limited, we take only one recent cross-lingual method (MT-CNN) proposed by Deriu et al [23] for comparison. It also relies on large-scale unlabeled Tweets and a translation tool.…”

Section: Generalizabilitymentioning

confidence: 99%

“…As the sentiment-labeled Tweets used by [23] are released in forms of Twitter IDs and some of them are no longer available now, we cannot directly compare our model to the reported results in [23]. For fair comparison, we reproduce their method on the labeled Tweets that can still be collected.…”

Section: Generalizabilitymentioning

confidence: 99%

See 2 more Smart Citations

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification

Chen

Shen

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

Sentiment classification typically relies on a large amount of labeled data. In practice, the availability of labels is highly imbalanced among different languages, e.g., more English texts are labeled than texts in any other languages, which creates a considerable inequality in the quality of related information services received by users speaking different languages. To tackle this problem, crosslingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i.e., the source language, usually English) to another language with fewer labels (i.e., the target language). The source and the target languages are usually bridged through off-the-shelf machine translation tools. Through such a channel, cross-language sentiment patterns can be successfully learned from English and transferred into the target languages. This approach, however, often fails to capture sentiment knowledge specific to the target language, and thus compromises the accuracy of the downstream classification task. In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. We propose a novel representation learning method that uses emoji prediction as an instrument to learn respective sentiment-aware representations for each language. The learned representations are then integrated to facilitate cross-lingual sentiment classification. The proposed method demonstrates state-of-the-art performance on benchmark datasets, which is sustained even when sentiment labels are scarce.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Generalizabilitymentioning

confidence: 99%

See 1 more Smart Citation

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification

Chen

Shen

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

show abstract

“…Examples are in semantic analysis (Shen et al, 2014), machine translation and sentiment analysis (Socher et al, 2013). In particular, shallow convolutional neural networks (CNNs) have recently improved the state-of-the-art in text polarity classification demonstrating a significant increase in terms of accuracy compared to previous state-of-the-art techniques (Kim, 2014;Kalchbrenner et al, 2014;dos Santos and Gatti, 2014;Severyn and Moschitti, 2015;Johnson and Zhang, 2015;Rothe et al, 2016;Deriu et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

A Twitter Corpus and Benchmark Resources for German Sentiment Analysis

Cieliebak¹,

Deriu²,

Egger³

et al. 2017

Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media

Self Cite

View full text Add to dashboard Cite

In this paper we present SB10k, a new corpus for sentiment analysis with approx. 10,000 German tweets. We use this new corpus and two existing corpora to provide state-of-the-art benchmarks for sentiment analysis in German: we implemented a CNN (based on the winning system of SemEval-2016) and a feature-based SVM and compare their performance on all three corpora. For the CNN, we also created German word embeddings trained on 300M tweets. These word embeddings were then optimized for sentiment analysis using distant-supervised learning. The new corpus, the German word embeddings (plain and optimized), and source code to re-run the benchmarks are publicly available.

show abstract

“…They intended to learn the previously unseen sentimental words from the big parallel corpus. Some studies have attempted to address multi-lingual sentiment classification (Deriu et al, 2017), but different from our study, they directly leverage training data in multiple languages, by assuming the training data can be obtained directly or in a distant supervision way in each language, and they did not consider the resource or data transfer problem at all.…”

Section: Related Workmentioning

confidence: 99%

Towards a Universal Sentiment Classifier in Multiple languages

Xu¹,

Wan

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Existing sentiment classifiers usually work for only one specific language, and different classification models are used in different languages. In this paper we aim to build a universal sentiment classifier with a single classification model in multiple different languages. In order to achieve this goal, we propose to learn multilingual sentiment-aware word embeddings simultaneously based only on the labeled reviews in English and unlabeled parallel data available in a few language pairs. It is not required that the parallel data exist between English and any other language, because the sentiment information can be transferred into any language via pivot languages. We present the evaluation results of our universal sentiment classifier in five languages, and the results are very promising even when the parallel data between English and the target languages are not used. Furthermore, the universal single classifier is compared with a few cross-language sentiment classifiers relying on direct parallel data between the source and target languages, and the results show that the performance of our universal sentiment classifier is very promising compared to that of different crosslanguage classifiers in multiple target languages.

show abstract

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification

Cited by 95 publications

References 20 publications

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification

A Twitter Corpus and Benchmark Resources for German Sentiment Analysis

Towards a Universal Sentiment Classifier in Multiple languages

Contact Info

Product

Resources

About