Sentiment Strength Research Articles

Distance-reconstructed dependency enhanced aspect-based sentiment analysis with sentiment strength

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that requires the detection of sentiment polarity towards specific aspects. Dependency tree-based graph convolutional network models (GCN) have been widely applied in ABSA. These studies utilize syntactic analysis tools to derive syntactic dependency graphs, which are then inputted into GCN. It enables iterative learning of sentiment dependency information from contextual words to aspect terms. However, directly using syntactic dependency graphs can lead to two shortcomings. First, the long-distance sentiment information in long sentences will be weakened during GCN iterative computations. Second, the syntactic dependency graphs of short sentences lack sentiment strength information. To address these two shortcomings, we propose a Distance-Reconstructed Dependency Enhanced Sentiment analysis approach with Sentiment Strength based on GCN (DRD-SE-GCN) approach, in which the syntactic dependency graph of long sentences is reconstructed based on distance, thus narrowing the gap between sentiment words and target aspect words. It ensures that the sentiment dependency information carried by the long-distance sentiment words will not be weakened or lost during the GCN iteration. Additionally, the weights of the syntactic dependency graph for short sentences are reassigned so as to carry the strength information of sentiment words. Experimental results on four standard datasets show that our proposed model can effectively improve the accuracy of aspect-level sentiment analysis.

Predicting word vectors for microtext

AbstractThe use of computer‐mediated communication has resulted in a new form of written text called Microtext, which is very different from well‐written text. Most previous approaches deal with microtext at the character level rather than just words resulting in increased processing time. In this paper, we propose to transform static word vectors to dynamic form by modelling the effect of neighbouring words and their sentiment strength in the AffectiveSpace. To evaluate the approach, we crawled Tweets from diverse topics and human annotation was used to label their sentiments. We also normalized the tweets to fix phonetic variations, spelling errors, and abbreviations manually. A total of 1432 out‐of‐vocabulary (OOV) texts and their IV texts made it to the final corpus with their corresponding polarity. To assess the quality of the corpus, we used several OOV classifiers such as linear regression and observed over 90% accuracy. Next, we inferred word vectors using a novel four‐gram model based on sentiment intensity and reported accuracy on both open domain and closed domain sentiment classifiers. We observed an improvement in the range of 4–20 on Twitter, Movie and Airline reviews over baselines.

Improve the application of reinforcement learning and multi‐modal information in music sentiment analysis

AbstractIn order to improve the effect of music sentiment analysis, this paper proposes a music sentiment classification method based on lyrics and comments. This method combines lyrics and comment texts to mine richer sentiment information, and comprehensively considers the influence of the word frequency, sentiment strength and part of speech of sentiment words on sentiment classification when constructing sentiment vectors. Moreover, it matches the lyrics of the music and the substantive words in the comment with the emotional dictionary to obtain the emotional category and emotional weight of each substantive word, and calculates the statistical value of each emotional category. In addition, this paper combines reinforcement learning and multi‐modal information technology to construct a music emotion research model.

STRESS PREDICTION USING MACHINE LEARNING

Every year tens of millions of people suffer from depression and few of them get proper treatment on time. So, it is crucial to detect human stress and relaxation automatically via social media on a timely basis. It is very important to detect and manage stress before it goes into a severe problem. A huge number of informal messages are posted every day in social networking sites, blogs and discussion forums. This paper describes an approach to detect the stress using the information from social media networking sites, like tweeter.This paper presents a method to detect expressions of stress and relaxation on tweeter dataset i.e. working on sentiment analysis to find emotions or feelings about daily life. Sentiment analysis works the automatic extraction of sentiment related information from text. Here using TensiStrengthframework for sentiment strength detection on social networking sites to extract sentiment strength from the informal English text. TensiStrength is a system todetect the strength of stress and relaxation expressed in social media text messages. TensiStrength uses a lexical approach and a set of rules to detect direct and indirect expressions of stress or relaxation. This classifies both positive and negative emotions based on the strength scale from -5 to +5 indications of sentiments. Stressed sentences from the conversation are considered &categorised into stress and relax. TensiStrength is robust, it can be applied to a widevarietyofdifferent social web contexts. Theeffectiveness of TensiStrength depends on the nature of the tweets.In human being there is inborn capability to differentiate the multiple senses of an ambiguous word in a particular context, but machine executes only according to the instructions. The major drawback of machine translation is Word Sense Disambiguation. There is a fact that a single word can have multiple meanings or "senses." In the pre-processing part- of- speech disambiguation is analysed and the drawback of WSD overcomes in the proposed method by unigram, bigram and trigram to give better result on ambiguous words. Here, SVM with Ngram gives better resultPrecision is65% and Recall is 67% .But, the main objective of this technique is to find the explicit and implicit amounts of stress and relaxation expressed in tweets. Keywords: Stress Detection, Data Mining, TensiStrength, wordsense disambiguation.

PS-Mixer: A Polar-Vector and Strength-Vector Mixer Model for Multimodal Sentiment Analysis

Multimodal sentiment analysis aims to judge the sentiment of multimodal data uploaded by the Internet users on various social media platforms. On one hand, existing studies focus on the fusion mechanism of multimodal data such as text, audio and visual, but ignore the similarity of text and audio, text and visual, and the heterogeneity of audio and visual, resulting in deviation of sentiment analysis. On the other hand, multimodal data brings noise irrelevant to sentiment analysis, which affects the effectness of fusion. In this paper, we propose a Polar-Vector and Strength-Vector mixer model called PS-Mixer, which is based on MLP-Mixer, to achieve better communication between different modal data for multimodal sentiment analysis. Specifically, we design a Polar-Vector (PV) and a Strength-Vector (SV) for judging the polar and strength of sentiment separately. PV is obtained from the communication of text and visual features to decide the sentiment that is positive, negative, or neutral sentiment. SV is gained from the communication between the text and audio features to analyze the sentiment strength in the range of 0 to 3. Furthermore, we devise an MLP-Communication module (MLP-C) composed of several fully connected layers and activation functions to make the different modal features fully interact in both the horizontal and the vertical directions, which is a novel attempt to use MLP for multimodal information communication. Finally, we mix PV and SV to obtain a fusion vector to judge the sentiment state. The proposed PS-Mixer is tested on two publicly available datasets, CMU-MOSEI and CMU-MOSI, which achieves the state-of-the-art (SOTA) performance on CMU-MOSEI compared with baseline methods. The codes are available at: https://github.com/metaphysicser/PS-Mixer.

Resilience of political leaders and healthcare organizations during COVID-19.

This study assesses the online societal association of leaders and healthcare organizations from the top-10 COVID-19 resilient nations through public engagement, sentiment strength, and inclusivity and diversity strength. After analyzing 173,071 Tweets authored by the leaders and health organizations, our findings indicate that United Arab Emirate’s Prime Minister had the highest online societal association (normalized online societal association: 1.000) followed by the leaders of Canada and Turkey (normalized online societal association: 0.068 and 0.033, respectively); and among the healthcare organizations, the Public Health Agency of Canada was the most impactful (normalized online societal association: 1.000) followed by the healthcare agencies of Turkey and Spain (normalized online societal association: 0.632 and 0.094 respectively). In comparison to healthcare organizations, the leaders displayed a strong awareness of individual factors and generalized their Tweets to a broader audience. The findings also suggest that users prefer accessing social media platforms for information during health emergencies and that leaders and healthcare institutions should realize the potential to use them effectively.

Spatial-Temporal Pattern Evolution of Public Sentiment Responses to the COVID-19 Pandemic in Small Cities of China: A Case Study Based on Social Media Data Analysis.

The impact of the COVID-19 pandemic on public mental health has become increasingly prominent. Therefore, it is of great value to study the spatial-temporal characteristics of public sentiment responses to COVID-19 exposure to improve urban anti-pandemic decision-making and public health resilience. However, the majority of recent studies have focused on the macro scale or large cities, and there is a relative lack of adequate research on the small-city scale in China. To address this lack of research, we conducted a case study of Shaoxing city, proposed a spatial-based pandemic-cognition-sentiment (PCS) conceptual model, and collected microblog check-in data and information on the spatial-temporal trajectory of cases before and after a wave of the COVID-19 pandemic. The natural language algorithm of dictionary-based sentiment analysis (DSA) was used to calculate public sentiment strength. Additionally, local Moran’s I, kernel-density analysis, Getis-Ord Gi* and standard deviation ellipse methods were applied to analyze the nonlinear evolution and clustering characteristics of public sentiment spatial-temporal patterns at the small-city scale concerning the pandemic. The results reveal that (1) the characteristics of pandemic spread show contagion diffusion at the micro level and hierarchical diffusion at the macro level, (2) the pandemic has a depressive effect on public sentiment in the center of the outbreak, and (3) the pandemic has a nonlinear gradient negative impact on mood in the surrounding areas. These findings could help propose targeted pandemic prevention policies applying spatial intervention to improve residents’ mental health resilience in response to future pandemics.

Tweets on a horror movie: An investigation into relationships between sentiment strength, cognitive language and tweet virality

This article studies how sentiment strength and cognitive language may influence the levels of tweet virality. A total of 11,381 tweets about a horror movie (‘Mother!’) were collected. Based on the definitions of two independent variables: sentiment strength and cognitive language use, and the dependent variable: tweet virality, the data descriptive statistics and analysis of variance (ANOVA) analysis were applied to reveal the relationships between tweet virality and sentiment and cognitive factors. The results indicate that a high tweet virality is associated with either a lower level of sentiment strength or/and a higher level of cognitive language use by a statistically significant margin. This finding is more evident for negative tweets. The study findings help improve the understanding about sentimental and cognitive factors impacting tweet virality and guide the movie industry to improve marketing movie content to achieve high virality on social media. The conclusions can also be applied to other industries, government agencies, organisations and individuals who intend to quickly disseminate specific information on social media platforms.

Efficacy improvement of aspect-based sentiment analysis using enhanced rule –based approach and domain-specific lexicon (ERBA-DSL)

Since people express their opinions and feelings more openly than ever before, sentiment analysis proves to be a promising research area that effectively analyses the opinion expressed over the entities. In this context, Sentiment analysis is utilized to gather valuable insights from users’ opinions. These insights would benefit a lot for the business concerns and institutions to improve their respective products/services. Aspect-based sentiment analysis (ABSA) is the most robust technique that offers a more fine-grained analysis. The objective of this paper is to improve the efficacy of ABSA by framing a robust and enhanced set of rules. Several experiments were carried out to detect explicit and implicit aspects. The hybrid approach comprising of enhanced rule-based approach (ERBA) and domain-specific lexicon (DSL) is used to improve the solution of the aspect-based sentiment analysis problem. The proposed approach employs a domain-specific adjective-noun collocation list(DSANCL) tailored to the domain for fine-tuning the process of implicit aspect detection(IAD). The proposed model frames a new nine-point scale for measuring the sentiment strength by introducing a ternary classification of intensifiers based on their degree of intensification. The performance of the proposed model is evaluated using the university reviews dataset.

Sentiment Analysis of Public Tweets Towards the Emergence of SARS-CoV-2 Omicron Variant: A Social Media Analytics Framework

While different variants of COVID-19 dramatically affected the lives of millions of people across the globe, a new version of COVID-19, "SARS-CoV-2 Omicron," emerged. This paper analyzes the public attitude and sentiment towards the emergence of the SARS-CoV-2 Omicron variant on Twitter. The proposed approach relies on the text analytics of Twitter data considering tweets, retweets, and hashtags' main themes, the pandemic restriction, the efficacy of covid-19 vaccines, transmissible variants, and the surge of infection. A total of 18,737 tweets were pulled via Twitter Application Programming Interface (API) from December 3, 2021, to December 26, 2021, using the SentiStrength software that employs a lexicon of sentiment terms and a set of linguistic rules. The analysis was conducted to distinguish and codify subjective content and estimate the strength of positive and negative sentiment with an average of 95% confidence intervals based upon emotion strength scales of 1-5. It is found that negativity was dominated after the outbreak of Omicron and scored 31.01% for weak, 16.32% for moderate, 5.36% for strong, and 0.35% for very strong sentiment strength. In contrast, positivity decreased gradually and scored 16.48% for weak, 11.19% for moderate, 0.80% for strong, and 0.04% for very strong sentiment strength. Identifying the public emotional status would help the concerned authorities to provide appropriate strategies and communications to relieve public worries about pandemics.

Optimizing sentiment strength detection for classification for airline opinion texts

Short text is rapidly expanding, and it is critical to understand why. Unlike traditional documents, short text is short and sparse, making machine learning and text mining algorithms difficult to apply. The process of identifying and categorizing ideas expressed in a text into positive, negative, and neutral polarities is referred to as sentiment analysis. The selection of features for machine learning is critical. The evaluation of search engines is a critical topic in the field of information retrieval. Researchers can determine whether their new algorithms add value or should be scrapped by effectively evaluating their algorithms. Organizations create cutting-edge methods for assessing their performance. Social tags have become an important source of information in web 2.0 for making personalized recommendations by identifying user interests and preferences. The purpose of this research is to systematically represent the actual topics of tags, the content of items, and user interest in specific topics via popular tags based on the content of the tags, items, and topics. The goal of this paper is to propose an innovative method for identifying user topic interests using popular tags. This paper proposes a method for extracting the main features of short text at various granularity levels. One aspect of how the content of items is represented in this paper is through the use of popular tags, but the representation of user interests is also discussed. By analysing a small dataset of short text classifications, we were able to compare our proposed method to a state-of-the-art baseline. We reduced the classification error by 20% using two different analysis methods, while the other method reduced it by 16.68%. The original tags of users are used to generate topic interests, from which we identify popular tags. The popular tags are then used to generate topic interests using an autoencoder approach.

Integrating Character-level and Word-level Representation for Affect in Arabic Tweets

Affect tasks, which range from sentiment polarity classification to finer grained sentiment strength and emotional intensity detection, have become of increasing interest due to the vast amount of user-generated content and advanced learning models. Word representation models have been leveraged effectively within a variety of natural language processing tasks. However, these models are not always effective in the context of social media. When dealing with social media posts in Arabic, the use of Arabic dialects needs to be considered. Although using informal text to train word-level models can lead to the identification of words that convey the same meaning, these models are unable to capture the full extent of the words that are used in the real world due to out-of-vocabulary (OOV) words. The inability to identify such words is one of the main limitations of word-level models. One approach of overcoming OOV is through the use of character-level embeddings as they can effectively learn the vectors of word parts or character n-grams. This study uses a combination of character-level and word-level models to identify the most effective methods by which affective Arabic words in tweets can be represented semantically and morphologically. We evaluate our generated models and the proposed method by integrating them in a supervised learning framework that was used for a range of affect tasks and other related tasks. Our findings reveal that the developed models surpassed the performance of state-of-the-art Arabic pre-trained word embeddings over eight datasets. In addition, our models enhance previous state-of-the-art outcomes on tasks involving Arabic emotion intensity, outperforming the top-systems that used advanced ensemble learning models and several additional features.

The merits of a sentiment analysis of antecedent comments for the prediction of online fundraising outcomes

This study focuses on the predictive power of online reviews on fundraising outcomes. Based on when the review is posted, we divide these online reviews into antecedent comments, made at the prelaunch and financing stages, and posterior comments, after the fundraising stage. Then, we conduct a sentiment analysis of these online reviews with a variety of algorithms to determine which one is best at sentiment extraction, finding that the deep learning algorithm is more effective than the shallow learning algorithms. Using fastText, we find that, as financing progresses, sentiment in the comments gradually turns negative, and sentiment strength is lower for successfully funded projects than for failed projects. The reason for this pessimistic turn is the topic discussed at various stages. FNN performs better than other approaches in the prediction of successful fundraising outcomes, with the addition of the antecedent online comments’ sentiment factor. Other prediction algorithms also show some degree of improvement with the addition of sentiment extracted from antecedent online reviews, which confirms the predictive power of antecedent comments. This study enhances the identification of the economic value of antecedent online reviews with the addition of sentiment analysis and shows a path for further developing internet finance.

Differential effects of online signals on sales performance of local brand clothing products

PurposeBusinesses need to make quick decisions and adjustments to fulfill the growing online demand. Previous studies examined various factors affecting the online sales performance of products such as books, electronics and movies; however, they paid limited attention toward the local brand clothing products. The current study investigates the importance of different kinds of seller-generated and consumer-generated signals such as price, discount, product ratings, review volume, review sentiment, number of questions and interaction between some of these factors for predicting the sales performance of clothing products.Design/methodology/approachThe multiple linear regressions has been employed to investigate the influence of various predictor variables on sales performance. The study also examines the importance of these predictor variables by using different machine learning models, including random forest (RF), neural networks and support vector regression (SVR).FindingsThe findings of the study emphasize the importance of price and discount rates offered on the product. The quantitative characteristics of reviews, such as review volume and average rating, have been found to be more important predictors than sentiment strengths. However, the sentiment strength of reviews with higher helpfulness scores plays a significant role in predicting sales performance.Originality/valueThe study highlights the varying importance of seller-based and consumer-based signals in predicting sales performance. It also investigates the interaction effect of these two kinds of signals. The consumer-generated signals have been further divided into two components based on social influence theory, and the interaction effects of these components have also been examined.

How text sentiment moderates the impact of motivational cues on crowdfunding campaigns

Arousing funders’ motives for crowdfunding participation is a challenge for every entrepreneur. According to self-determination theory, crowdfunding involvement is driven by two kinds of motivations: extrinsic and intrinsic motives. Campaign narratives with different sentimental orientations could act as cues triggering funders’ motives of capital-giving differently. Thus, we focus on the moderating effect of text sentiment on the motivational cues in crowdfunding campaigns. We hypothesize that the sentiment of campaign narratives moderates the relationship between motivational cues and fundraising success. Data are selected from 270,000 campaigns of the crowdfunding website Indiegogo. Empirical analysis demonstrates that the sentiment strength positively moderates the effect of intrinsic motives on fundraising success but negatively moderates the impact of extrinsic motives on fundraising success. The findings provide managerial insights for practitioners to stimulate specified motives by using the narratives with proper sentiment strength.

Detecting Urban Events by Considering Long Temporal Dependency of Sentiment Strength in Geotagged Social Media Data

The development of location-based services facilitates the use of location data for detecting urban events. Currently, most studies based on location data model the pattern of an urban dynamic and then extract the anomalies, which deviate significantly from the pattern as urban events. However, few studies have considered the long temporal dependency of sentiment strength in geotagged social media data, and thus it is difficult to further improve the reliability of detection results. In this paper, we combined a sentiment analysis method and long short-term memory neural network for detecting urban events with geotagged social media data. We first applied a dictionary-based method to evaluate the positive and negative sentiment strength. Based on long short-term memory neural network, the long temporal dependency of sentiment strength in geotagged social media data was constructed. By considering the long temporal dependency, daily positive and negative sentiment strength are predicted. We extracted anomalies that deviated significantly from the prediction as urban events. For each event, event-related information was obtained by analyzing social media texts. Our results indicate that the proposed approach is a cost-effective way to detect urban events, such as festivals, COVID-19-related events and traffic jams. In addition, compared to existing methods, we found that accounting for a long temporal dependency of sentiment strength can significantly improve the reliability of event detection.

MTVRep: A movie and TV show reputation system based on fine-grained sentiment and semantic analysis

Customer reviews are a valuable source of information from which we can extract very useful data about different online shopping experiences. For trendy items (products, movies, TV shows, hotels, services . . . ), the number of available users and customers’ opinions could easily surpass thousands. Therefore, online reputation systems could aid potential customers in making the right decision (buying, renting, booking . . . ) by automatically mining textual reviews and their ratings. This paper presents MTVRep, a movie and TV show reputation system that incorporates fine-grained opinion mining and semantic analysis to generate and visualize reputation toward movies and TV shows. Differently from previous studies on reputation generation that treat the task of sentiment analysis as a binary classification problem (positive, negative), the proposed system identifies the sentiment strength during the phase of sentiment classification by using fine-grained sentiment analysis to separate movie and TV show reviews into five discrete classes: strongly negative, weakly negative, neutral, weakly positive and strongly positive. Besides, it employs embeddings from language models (ELMo) representations to extract semantic relations between reviews. The contribution of this paper is threefold. First, movie and TV show reviews are separated into five groups based on their sentiment orientation. Second, a custom score is computed for each opinion group. Finally, a numerical reputation value is produced toward the target movie or TV show. The efficacy of the proposed system is illustrated by conducting several experiments on a real-world movie and TV show dataset.

Using Geotagged Social Media Data to Explore Sentiment Changes in Tourist Flow: A Spatiotemporal Analytical Framework

Understanding sentiment changes in tourist flow is critical in designing exciting experiences for tourists and promoting sustainable tourism development. This paper proposes a novel analytical framework to investigate the tourist sentiment changes between different attractions based on geotagged social media data. Our framework mainly focuses on visualizing the detailed sentiment changes of tourists and exploring the valuable spatiotemporal pattern of the sentiment changes in tourist flow. The tourists were first identified from social media users. Then, we accurately evaluated the tourist sentiment by constructing a Chinese sentiment dictionary, grammatical rule, and sentiment score. Based on the location information of social media data, we built and visualized the tourist flow network. Last, to further reveal the impact of attractions on the sentiment of tourist flow, the positive and negative sentiment profiles were generated by mining social media texts. We took Beijing, a famous tourist destination in China, as a case study. Our results revealed the following: (1) the temporal trend of tourist sentiment has seasonal characteristics and is significantly influenced by government control policies against COVID-19; (2) due to the impact of the attraction’s historical background, some tourist flows with highly decreased sentiment strength are linked to attractions; (3) on the long journey to the attraction, the sentiment strength of tourists decreases; and (4) bad traffic conditions can significantly decrease tourist sentiment. This study highlights the methodological implications of visualizing sentiment changes during collective tourist movement and provides comprehensive insight into the spatiotemporal pattern of tourist sentiment.

Enhancing Contextualised Language Models with Static Character and Word Embeddings for Emotional Intensity and Sentiment Strength Detection in Arabic Tweets

Many studies have focused on Arabic sentiment or emotion classification tasks. However, research on alternative aspects of affect, such as emotional intensity and sentiment strength tasks, has been somewhat limited. In this paper, we propose a method for enriching a contextualised language model that incorporates static character and word embeddings for emotional intensity and sentiment strength in Arabic tweets. We examine the assumption that models using static embeddings that are trained specifically on a corpus containing extensive Arabic affect-related words can boost the performance of language models. Through the development of character-level embeddings, we have found that our method is able to overcome the limitations associated with out-of-vocabulary words, which is a common problem when dealing with Arabic informal text. Given this, the method that we have developed achieves state-of-the-art results for the detection of the intensity of emotion and sentiment strength in Arabic social media.

Prediction of Opinion Keywords and Their Sentiment Strength Score Using Latent Space Learning Methods

Most item-shopping websites give people the opportunity to express their thoughts and opinions on items available for purchasing. This information often includes both ratings and text reviews expressing somehow their tastes and can be used to predict their future opinions on items not yet reviewed. Whereas most recommendation systems have focused exclusively on ranking the items based on rating predictions or user-modeling approaches, we propose an adapted recommendation system based on the prediction of opinion keywords assigned to different item characteristics and their sentiment strength scores. This proposal makes use of natural language processing (NLP) tools for analyzing the text reviews and is based on the assumption that there exist common user tastes which can be represented by latent review topics models. This approach has two main advantages: is able to predict interpretable textual keywords and its associated sentiment (positive/negative) which will help to elaborate a more precise recommendation and justify it, and allows the use of different dictionary sizes to balance performance and user opinion interpretability. To prove the feasibility of the adapted recommendation system, we have tested the capabilities of our method to predict the sentiment strength score of item characteristics not previously reviewed. The experimental results have been performed with real datasets and the obtained F1 score ranges from 66% to 77% depending on the dataset used. Moreover, the results show that the method can generalize well and can be applied to combined domain independent datasets.