•A LinearSVM model was able to extract e-mail sentiment with a mean AUC of 0.896.•The model could also predict sentiment for e-mail responses with a mean AUC of 0.805.•The results suggests ...possibilities for improved customer support mangement processes.
Customer support is important to corporate operations, which involves dealing with disgruntled customer and content customers that can have different requirements. As such, it is important to quickly extract the sentiment of support errands. In this study we investigate sentiment analysis in customer support for a large Swedish Telecom corporation. The data set consists of 168,010 e-mails divided into 69,900 conversation threads without any sentiment information available. Therefore, VADER sentiment is used together with a Swedish sentiment lexicon in order to provide initial labeling of the e-mails. The e-mail content and sentiment labels are then used to train two Support Vector Machine models in extracting/classifying the sentiment of e-mails. Further, the ability to predict sentiment of not-yet-seen e-mail responses is investigated. Experimental results show that the LinearSVM model was able to extract sentiment with a mean F1-score of 0.834 and mean AUC of 0.896. Moreover, the LinearSVM algorithm was also able to predict the sentiment of an e-mail one step ahead in the thread (based on the text in the an already sent e-mail) with a mean F1-score of 0.688 and the mean AUC of 0.805. The results indicate a predictable pattern in e-mail conversation that enables predicting the sentiment of a not-yet-seen e-mail. This can be used e.g. to prepare particular actions for customers that are likely to have a negative response. It can also provide feedback on possible sentiment reactions to customer support e-mails.
Abstract Aspect-Based Sentiment Analysis (ABSA) represents a fine-grained approach to sentiment analysis, aiming to pinpoint and evaluate sentiments associated with specific aspects within a text. ...ABSA encompasses a set of sub-tasks that together facilitate a detailed understanding of the multifaceted sentiment expressions. These tasks include aspect and opinion terms extraction (ATE and OTE), classification of sentiment at the aspect level (ALSC), the coupling of aspect and opinion terms extraction (AOE and AOPE), and the challenging integration of these elements into sentiment triplets (ASTE). Our research introduces a comprehensive framework capable of addressing the entire gamut of ABSA sub-tasks. This framework leverages the contextual strengths of BERT for nuanced language comprehension and employs a biaffine attention mechanism for the precise delineation of word relationships. To address the relational complexity inherent in ABSA, we incorporate a Multi-Layered Enhanced Graph Convolutional Network (MLEGCN) that utilizes advanced linguistic features to refine the model’s interpretive capabilities. We also introduce a systematic refinement approach within MLEGCN to enhance word-pair representations, which leverages the implicit outcomes of aspect and opinion extractions to ascertain the compatibility of word pairs. We conduct extensive experiments on benchmark datasets, where our model significantly outperforms existing approaches. Our contributions establish a new paradigm for sentiment analysis, offering a robust tool for the nuanced extraction of sentiment information across diverse text corpora. This work is anticipated to have significant implications for the advancement of sentiment analysis technology, providing deeper insights into consumer preferences and opinions for a wide range of applications.
A survey on sentiment analysis challenges Hussein, Doaa Mohey El-Din Mohamed
Journal of King Saud University. Engineering sciences,
October 2018, 2018-10-00, 2018-10-01, Letnik:
30, Številka:
4
Journal Article
Recenzirano
Odprti dostop
With accelerated evolution of the internet as websites, social networks, blogs, online portals, reviews, opinions, recommendations, ratings, and feedback are generated by writers. This writer ...generated sentiment content can be about books, people, hotels, products, research, events, etc. These sentiments become very beneficial for businesses, governments, and individuals. While this content is meant to be useful, a bulk of this writer generated content require using the text mining techniques and sentiment analysis. But there are several challenges facing the sentiment analysis and evaluation process. These challenges become obstacles in analyzing the accurate meaning of sentiments and detecting the suitable sentiment polarity. Sentiment analysis is the practice of applying natural language processing and text analysis techniques to identify and extract subjective information from text. This paper presents a survey on the sentiment analysis challenges relevant to their approaches and techniques.
Micro-blog texts contain complex and abundant sentiments which reflect user’s standpoints or opinions on a given topic. However, the existing classification method of sentiments cannot facilitate ...micro-blog topic monitoring. To solve this problem, this paper presents a sentiment analysis method for Chinese micro-blog text based on the sentiment dictionary to support network regulators’ work better. First, the sentiment dictionary can be extended by extraction and construction of degree adverb dictionary, network word dictionary, negative word dictionary and other related dictionaries. Second, the sentiment value of a micro-blog text can be obtained through the calculation of the weight. Finally, micro-blog texts on a topic can be classified as positive, negative and neutral. Experimental results show the effectiveness of the proposed method.
•Micro-blog texts contain abundant sentiments which reflect users opinions.•The existing sentimental classification method cannot help micro-blog topic monitoring•This paper presents a sentiment analysis method for Chinese micro -blog text.•Three simplified sentiments are easily support micro-blog topic monitoring.
Aspect-level sentiment classification aims to distinguish the sentiment polarities over one or more aspect terms in a sentence. Existing approaches mostly model different aspects in one sentence ...independently, which ignore the sentiment dependencies between different aspects. However, such dependency information between different aspects can bring additional valuable information for aspect-level sentiment classification. In this paper, we propose a novel aspect-level sentiment classification model based on graph convolutional networks (GCN) which can effectively capture the sentiment dependencies between multi-aspects in one sentence. Our model firstly introduces bidirectional attention mechanism with position encoding to model aspect-specific representations between each aspect and its context words, then employs GCN over the attention mechanism to capture the sentiment dependencies between different aspects in one sentence. The proposed approach is evaluated on the SemEval 2014 datasets. Experiments show that our model outperforms the state-of-the-art methods. We also conduct experiments to evaluate the effectiveness of GCN module, which indicates that the dependencies between different aspects are highly helpful in aspect-level sentiment classification11Source code is available at https://github.com/Pinlong-Zhao/SDGCN..
To provide explainable and accurate aspect terms and the corresponding aspect–sentiment detection, it is often useful to take external domain-specific knowledge into consideration. In this work, we ...propose a knowledge-enabled language representation model BERT for aspect-based sentiment analysis. Specifically, our proposal leverages the additional information from a sentiment knowledge graph by injecting sentiment domain knowledge into the language representation model, which obtains the embedding vectors of entities in the sentiment knowledge graph and words in the text in a consistent vector space. In addition, the model is capable of achieving better performance with a small amount of training data by incorporating external domain knowledge into the language representation model to compensate for the limited training data. As a result, our model is able to provide explainable and detailed results for aspect-based sentiment analysis. Experimental results demonstrate the effectiveness of the proposed method, showing that the knowledge-enabled BERT is an excellent choice for solving aspect-based sentiment analysis problems.
•External knowledge is used for improving the performance of aspect based sentiment analysis.•We study the problem of explainable aspect-based sentiment analysis by leveraging a sentiment knowledge graph to better capture the sentiment relations between aspects and sentiment terms.•We propose incorporating external knowledge into the BERT to obtain the embedding vectors for aspect based sentiment analysis.
Online forwarding behavior, which involves users sharing information through URLs on social media platforms, has been extensively acknowledged as important to businesses, society, and individuals. ...Although previous research has discussed its antecedents from the sentiment perspective, most of them focus on the effect size, without differentiating the distinct effects of positive and negative sentiment. This study not only tests the association between positive (negative) sentiment and online forwarding but also examines how the aforementioned association varies from sentiment dispersion, measured by the variance of sentiment between individuals and groups (i.e., positive vs. negative sentiment dispersions); and sentiment dissimilarity, measured by the inconsistency between review content and title in terms of sentiment (i.e., positive vs. negative sentiment dissimilarities). Analysis of the data set collected from TripAdvisor yields the following findings: (1) positive sentiment negatively affects forwarding behavior, (2) negative sentiment positively affects forwarding behavior, (3) positive sentiment dispersion strengthens the negative effect of positive sentiment, but the moderation effect of positive sentiment dissimilarity is insignificant, and (4) negative sentiment dispersion/dissimilarity dampens the positive effect of negative sentiment. Findings extend our understanding of sentiment and online forwarding by highlighting the heterogeneous effects of positive and negative sentiments, thereby providing suggestions for forwarding function design.
Sentiment analysis, which refers to the task of detecting whether a textual item (e.g., a product review and a blog post) expresses a positive or negative opinion in general or about a given entity ...(e.g., a product, person, or policy), has received increasing attention in recent years. It serves as an important role in natural language processing. User generated content, like tourism reviews, developed dramatically during the past years, generating a large amount of unstructured data from which it is hard to obtain useful information. Due to the changes in textual order, sequence length and complicated logic, it is still a challenging task to predict the exact sentiment polarities of the user reviews, especially for fine-grained sentiment classification. In this paper, we first propose sentiment padding, a novel padding method compared with zero padding, making the input data sample of a consistent size and improving the proportion of sentiment information in each review. Inspired by the most recent studies with respect to neural networks, we propose deep learning based sentiment analysis models named lexicon integrated two-channel CNN–LSTM family models, combining CNN and LSTM/BiLSTM branches in a parallel manner. Experiments on several challenging datasets, like Stanford Sentiment Treebank, demonstrate that the proposed method outperforms many baseline methods.
•We proposed sentiment padding to improve the proportion of sentiment information in each review.•We presented lexicon integrated two-channel CNN–BiLSTM model.•This paper studied the influence of the skip connection operation on two-channel deep model.•Experiment showed superiority of the proposed model on analyzing English and Chinese reviews.
Sentiment analysis has come long way since it was introduced as a natural language processing task nearly 20 years ago. Sentiment analysis aims to extract the underlying attitudes and opinions toward ...an entity. It has become a powerful tool used by governments, businesses, medicine, marketing, and others. The traditional sentiment analysis model focuses mainly on text content. However, technological advances have allowed people to express their opinions and feelings through audio, image and video channels. As a result, sentiment analysis is shifting from unimodality to multimodality. Multimodal sentiment analysis brings new opportunities with the rapid increase of sentiment analysis as complementary data streams enable improved and deeper sentiment detection which goes beyond text-based analysis. Audio and video channels are included in multimodal sentiment analysis in terms of broadness. People have been working on different approaches to improve sentiment analysis system performance by employing complex deep neural architectures. Recently, sentiment analysis has achieved significant success using the transformer-based model. This paper presents a comprehensive study of different sentiment analysis approaches, applications, challenges, and resources then concludes that it holds tremendous potential. The primary motivation of this survey is to highlight changing trends in the unimodality to multimodality for solving sentiment analysis tasks.