Multilingual aspect clustering for sentiment analysis

Pessutto, Lucas Rafael Costella; Vargas, Danny Suarez; Moreira, Viviane Pereira

doi:10.1016/j.knosys.2019.105339

Cited by 20 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Big data in the context of the Internet has become an important force in promoting digital humanities research, and the analysis of sentiment tendencies in social media texts such as Twitter has been a hot topic of research in natural language processing [1]. German, one of the official languages of the United Nations and the eighth most spoken language in the world, is widely spoken in 17 countries in the Eastern European and Central Asian regions, and the total number of people who speak it as a native or second language is about 258 million [2]. As one of the main ways for people to communicate and express their emotions, social media generates a large amount of short texts in German with subjective emotions every day, and it is beneficial to summarize, analyze, and reason about the emotional information contained in them for making business decisions, analyzing political opinions, and predicting social trends in related countries [3].…”

Section: Introductionmentioning

confidence: 99%

Text Sentiment Analysis of German Multilevel Features Based on Self-Attention Mechanism

2021

Security and Communication Networks

View full text Add to dashboard Cite

In this paper, we propose a multilevel feature representation method that combines word-level features, such as German morphology and slang, and sentence-level features, such as special symbols and English-translated sentiment information, and build a deep learning model for German sentiment classification based on the self-attentive mechanism, in order to address the characteristics of German social media texts that are colloquial, irregular, and diverse. Compared with the existing studies, this model not only has the most obvious improvement effect but also has better feature extraction and classification ability for German emotion.

show abstract

Section: Introductionmentioning

confidence: 99%

Text Sentiment Analysis of German Multilevel Features Based on Self-Attention Mechanism

2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, the proposed method with empirical evidence is one of the earliest attempts in systematically building up a cross-lingual transferring framework for the entity relation extraction. Compared with the application of cross-lingual transferring to other tasks – for example, sentiment classification (Pessutto et al , 2020), topic analysis (Xie et al , 2020) and price forecasting (Li et al , 2020a, 2020b) – the ERE task needs more fine-grained label alignments between different languages. The diversities of alignments increase difficulties of the cross-lingual training, as some words from the source sentence might be paired with multiple target words, or even with no target word at all.…”

Section: Experiments and Discussionmentioning

confidence: 99%

“…At the same time, current research within big data organization mainly focuses on building systems and models using the English language (Kaity and Balakrishnan, 2020), despite the enormity of texts available in multiple other languages. Consequently, it becomes necessary to deal with multi-lingual data for many big data analysis tasks; for example, sentiment classification (Pessutto et al , 2020), topic analysis (Xie et al , 2020), price forecasting (Li et al , 2020a, 2020b) and so forth. Taking the task of entity relation extraction (ERE) as an example, there are abundant annotated corpus in English, while in other language contexts, tagged corpus is relatively scarce, and manual tagging for each language is an expensive and time-consuming task, especially for low resource languages (Catelli et al , 2020; Kim et al , 2014).…”

Section: Introductionmentioning

confidence: 99%

Towards an entity relation extraction framework in the cross-lingual context

Xue

Wang

et al. 2021

View full text Add to dashboard Cite

Purpose Owing to the uneven distribution of annotated corpus among different languages, it is necessary to bridge the gap between low resource languages and high resource languages. From the perspective of entity relation extraction, this paper aims to extend the knowledge acquisition task from a single language context to a cross-lingual context, and to improve the relation extraction performance for low resource languages. Design/methodology/approach This paper proposes a cross-lingual adversarial relation extraction (CLARE) framework, which decomposes cross-lingual relation extraction into parallel corpus acquisition and adversarial adaptation relation extraction. Based on the proposed framework, this paper conducts extensive experiments in two tasks, i.e. the English-to-Chinese and the English-to-Arabic cross-lingual entity relation extraction. Findings The Macro-F1 values of the optimal models in the two tasks are 0.880 1 and 0.789 9, respectively, indicating that the proposed CLARE framework for CLARE can significantly improve the effect of low resource language entity relation extraction. The experimental results suggest that the proposed framework can effectively transfer the corpus as well as the annotated tags from English to Chinese and Arabic. This study reveals that the proposed approach is less human labour intensive and more effective in the cross-lingual entity relation extraction than the manual method. It shows that this approach has high generalizability among different languages. Originality/value The research results are of great significance for improving the performance of the cross-lingual knowledge acquisition. The cross-lingual transfer may greatly reduce the time and cost of the manual construction of the multi-lingual corpus. It sheds light on the knowledge acquisition and organization from the unstructured text in the era of big data.

show abstract

“…Finally, in step 11, the popular aspects (A) are extracted by measuring the similarity between the two sets, candidate aspects (Ac) and direct aspects (Ad), using the “SemanticSimilarity” function. This function implements word embedding, which has shown great results in handling the semantic similarity, as in [ 31 ]. For example, the customer review “This laptop runs fast, but the only problem that the touch screen was not responsive and the resolution is amazing.” has four candidate aspects (Ac) represented by three nouns (“laptop,” “problem,” and “resolution”) and one noun phrase (“touch screen”).…”

Section: Seopinion: Methodologymentioning

confidence: 99%

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Mabrouk

Redondo

Kayed

2021

Sensors

View full text Add to dashboard Cite

Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers’ opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.

show abstract

Multilingual aspect clustering for sentiment analysis

Cited by 20 publications

References 15 publications

Text Sentiment Analysis of German Multilevel Features Based on Self-Attention Mechanism

Text Sentiment Analysis of German Multilevel Features Based on Self-Attention Mechanism

Towards an entity relation extraction framework in the cross-lingual context

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Contact Info

Product

Resources

About