Sentiment wEight of N-grams in Dataset (SEND): A Feature-set for Cross-domain Sentiment Classification

Dey, Atanu; Jenamani, Mamata; Thakkar, Jitesh J.

doi:10.1109/icapr.2017.8593172

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An exclamation or even a punctuation change can cause a reversal of text sentiment, which leads to difficulties in text annotation. Secondly, it is difficult to classify sentiment, and sometimes it is difficult to precisely understand the real sentiment from a sentence (often need to combine with contextual information), which leads to difficulty in sentiment recognition [22].…”

Section: Text Sentiment Analysismentioning

confidence: 99%

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

Duan

Shen

Luo

2022

IJERPH

View full text Add to dashboard Cite

As the relationship between the built environment and the sense of human experience becomes increasingly important, emotional geography has begun to focus on sentiments in space and time and improving the quality of urban construction from the perspective of public emotion and mental health. While youth is a powerful force in urban construction, there are no studies on the relationship between urban youth sentiments and the built environment. With the development of the Internet, social media has provided a large source of data for the metrics of youth sentiment. Based on data from more than 10,000 geolocated Sina Weibo comments posted over one week (from 19 to 25 July 2021) in Shanghai and using a machine learning algorithm for attention mechanism, this study calculates the sentiment label and sentiment intensity of each comment. Ten elements in five aspects were selected to assess the built environment at different scales and also to explore the correlations between built environment elements and sentiment intensity at different scales. The study finds that the overall sentiment of Shanghai youth tends to be negative. Sentiment intensity is significantly associated with most built environment elements at smaller scales. Urban youth have a higher proportion of both happy and sad sentiments, within which sad sentiments are more closely related to the built environment and are significantly related to all built environment elements. This study uses a deep learning algorithm to improve the accuracy of sentiment classification and confirms that the built environment has a great impact on sentiment. This research can help cities develop built environment optimization measures and policies to create positive emotional environments and enhance the well-being of urban youth.

show abstract

Section: Text Sentiment Analysismentioning

confidence: 99%

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

Duan

Shen

Luo

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…Authony et al optimized n-gram-based text feature selection to improve the accuracy of sentiment analysis [19]. In [20], intensifiers and negations are extracted to construct n-gram features for cross-domain sentiment classification. e limitation of these two methods [19,20] is that they depend on the existed unigrams sentiment lexicons and do not provide sentiment values for the n-gram features.…”

Section: Related Workmentioning

confidence: 99%

A Training‐Optimization‐Based Method for Constructing Domain‐Specific Sentiment Lexicon

Luo

2021

Complexity

View full text Add to dashboard Cite

Sentiment analysis has been widely used in text mining of social media to discover valuable information from user reviews. Sentiment lexicon is an essential tool for sentiment analysis. Recent research studies indicate that constructing sentiment lexicons for special domains can achieve better results in sentiment analysis. However, it is not easy to construct a sentiment lexicon for a specific domain because most current methods highly depend on general sentiment lexicons and complex linguistic rules. In this paper, the construction of sentiment lexicon is transformed into a training-optimization process. In our scheme, the accuracy of sentiment classification is used as the optimization objective. The candidate sentiment lexicons are regarded as the individuals that need to be optimized. Then, two genetic algorithms are specially designed to adjust the values of sentiment words in lexicon. Finally, the best individual evolved in the presented genetic algorithms is selected as the sentiment lexicon. Our method only depends on some labelled texts and does not need any linguistic knowledge or prior knowledge. It provides a simple and easy way to construct a sentiment lexicon in a specific domain. Experiment results show that the proposed method has good flexibility and can generate high-quality sentiment lexicon in specific domains.

show abstract

“…In [24], cross-domain-labeled Web sources (Amazon and Tripadvisor) are used to train supervised learning models (including two deep learning algorithms) that are tested for typically unlabelled social media reviews (Facebook and Twitter), whose train model is tested on Facebook data for both English and Italian. In weight computing, Dey et al [25] calculated the sentiment score of the n-grams by using the individual sentiment scores of the unigrams and precalculated values of intensifiers and negations attached with it. ese scores are multiplied with the corresponding feature-importance value to generate the final score of SEND features of each review.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Structure for Cross-Domain Sentiment Classification Based on Improved Cross Entropy and Weight

Fei

Yao

Zhu

et al. 2020

Scientific Programming

View full text Add to dashboard Cite

Within the sentiment classification field, the convolutional neural network (CNN) and long short-term memory (LSTM) are praised for their classification and prediction performance, but their accuracy, loss rate, and time are not ideal. To this purpose, a deep learning structure combining the improved cross entropy and weight for word is proposed for solving cross-domain sentiment classification, which focuses on achieving better text sentiment classification by optimizing and improving recurrent neural network (RNN) and CNN. Firstly, we use the idea of hinge loss function (hinge loss) and the triplet loss function (triplet loss) to improve the cross entropy loss. The improved cross entropy loss function is combined with the CNN model and LSTM network which are tested in the two classification problems. Then, the LSTM binary-optimize (LSTM-BO) model and CNN binary-optimize (CNN-BO) model are proposed, which are more effective in fitting the predicted errors and preventing overfitting. Finally, considering the characteristics of the processing text of the recurrent neural network, the influence of input words for the final classification is analysed, which can obtain the importance of each word to the classification results. The experiment results show that within the same time, the proposed weight-recurrent neural network (W-RNN) model gives higher weight to words with stronger emotional tendency to reduce the loss of emotional information, which improves the accuracy of classification.

show abstract

Sentiment wEight of N-grams in Dataset (SEND): A Feature-set for Cross-domain Sentiment Classification

Cited by 4 publications

References 9 publications

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

A Training‐Optimization‐Based Method for Constructing Domain‐Specific Sentiment Lexicon

Deep Learning Structure for Cross-Domain Sentiment Classification Based on Improved Cross Entropy and Weight

Contact Info

Product

Resources

About