Sentiment Analysis Methodology Research Articles

A generalizable sentiment analysis method for creating a hotel dictionary: using big data on TripAdvisor hotel reviews

论可推广性的情感分析法以创建酒店字典：以TripAdvisor酒店评论为样本的大数据分析摘要研究目的对于在线游客评论的研究在过去的几年中与日俱增, 但是仍缺乏有效方法能在有限的时间喝预算内提供终端用户价值。本论文开发并测试了一套情感分析的新方法, 创建两套酒店相关的词库, 此方法超越了标准词典式分析法。研究设计/方法/途径研究样本为TripAdvisor酒店客户评论的大数据, 通过开发崭新的有配重的词库法, 来开展两极式情感分析。这个崭新的具有配重的词库法能够呈现透明化和可复制的程序, 准备、创建、并检验情感分析的词条。这个方法用到了两种词典（有配重的词典L1和手动选择的词典L2）, 本论文通过对TripAdvisor大数据进行使用词类划分精准度, 来检测和验证这两种词典。本论文采用两种热门方法（公共词典法和复杂机器学习算法）来对比词典的准确度。研究结果精确度对比结果证实了本论文的方法, 相较于机器学习算法, 显著地超越了以字典为基础的方法。研究结果还表明, 本论文的方法可以就预测用户情感趋势进行推广。研究实际启示本论文开发并验证了一项方法, 这种方法通过创建可信的词典进行大数据分析, 以判定用户情感。本论文创建的L2酒店词库对分析客人反馈是可靠有用的工具, 这个词库还能帮助酒店经理了解、预测、以及积极相应客人的态度和改变。本论文还提出了一项可以了解每个用户情感的简易方法, 这项方法可以通过对比的方式来检测和了解客人不同时间的情感变化, 以及根据其不同背景和经历的不同用户之间的变化。研究原创性/价值本论文提出并检测了一项新方法, 这项情感分析方法可以解决之前方法的局限并立脚于旅游行业。基于文献综述, 本论文是首篇研究, 使用词库法来进行情感分析和创建特别领域词典的方式。

Fine-Grained, Aspect-Based Sentiment Analysis on Economic and Financial Lexicon

The last two decades have seen a tremendous increase in the adoption of Semantic Web technologies as a result of the availability of big data, the growth in computational power and the advancement of artificial intelligence (AI) technologies. Cutting-edge semantic techniques are now able to capture sentiments more accurately in various practical applications, including economic and financial forecasting. In particular, the extraction of sentiment from news text, social media and blogs for the prediction of economic and financial variables has attracted attention in recent years. Despite many successful applications of sentiment analysis (SA) in these domains, the range of semantic techniques employed is still limited and mostly focused on the detection of sentiment at a coarse-grained level, that is, whether the sentiment expressed by the entire text of a sentence is either positive or negative. This paper proposes a novel methodology for Fine-Grained Aspect-based Sentiment (FiGAS) analysis. The aim of the approach is to identify the sentiment associated to specific topics of interest in each sentence of a document and assigning real-valued polarity scores between -1 and +1 to those topics. The proposed approach is completely unsupervised and customized to the economic and financial domains by using a specialized lexicon make available along with the source code of FiGAS. Our lexicon-based SA approach relies on a detailed set of semantic polarity rules that allow understanding the origin of sentiment, in the spirit of the recent trend on \textit{Interpretable AI}. We provide an in-depth comparison of the performance of the FiGAS algorithm relative to other popular lexicon-based SA approaches in predicting a humanly annotated data set in the economic and financial domains. Our results indicate that FiGAS statistically outperforms the other methods by providing a sentiment score that is closer to one of the human annotators.

An efficient methodology for aspect-based sentiment analysis using BERT through refined aspect extraction

Aspect-Based Sentiment Analysis (ABSA) has become a trending research domain due to its ability to transform lives as well as the technical challenges involved in it. In this paper, a unique set of rules has been formulated to extract aspect-opinion phrases. It helps to reduce the average sentence length by 84% and the complexity of the text by 50%. A modified rank-based version of Term-Frequency - Inverse-Document-Frequency (TF-IDF) has been proposed to identify significant aspects. An innovative word representation technique has been applied for aspect categorization which identifies both local as well as global context of a word. For sentiment classification, pre-trained Bidirectional Encoder Representations from Transformers (BERT) has been applied as it helps to capture long-term dependencies and reduce the overhead of training the model from scratch. However, BERT has drawbacks like quadratic drop in efficiency with an increase in sequence length which is limited to 512 tokens. The proposed methodology mitigates these drawbacks of a typical BERT classifier accompanied by a rise in efficiency along with an improvement of 8% in its accuracy. Furthermore, it yields enhanced performance and efficiency compared to other state-of-the-art methods. The assertions have been established through extensive analysis upon movie reviews and Sentihood data-sets.

Online Place Branding for Natural Heritage: Institutional Strategies and Users’ Perceptions of Mount Etna (Italy)

In recent years, tourist destinations and strategies of place branding have been facing new challenges owing to the diffusion of Information and Communications technologies. Smart devices can give tourists/prosumers the possibility to co-create and share their travel experience to the point to influence the destination web reputation and, consequently, its digital place image and branding. Furthermore, new technologies can be also used as effective analytical tools to scrutinize the role of online co-created narratives in influencing the web reputation of a specific tourist site, natural heritage included. The study focuses on the online destination image of Mount Etna, an active volcano located in Southern Italy inserted in the UNESCO World Heritage List since 2017. The web reputation of this natural heritage site has been analyzed through a twofold methodology: a manual online content analysis and a software-based Sentiment Analysis methodology. The paper highlights the crucial role of new technologies both as tools of analysis in tourism and heritage studies and as “catalysts” of e-narratives able to influence place images. In so doing, the research aims at providing other researchers and policy-makers with new theoretical and methodological insights about the challenges and potentialities of smart technologies in exploring the online place image, thus contributing to a novel conceptualization of place branding through the theoretical/operational framework of Place Branding 3.0. In particular, the mixed-method approach represents an innovative framework insofar as it provides an in-depth evaluation of users’ online perceptions both at the “micro” scale—at the level of contents, through the manual content analysis—as well as at the “macro” scale, thanks to the software-based Sentiment Analysis methodology.

Rome was not built in a day. Resilience and the eternal city: Insights for urban management

Resilience has been intensely investigated as the viable quality of individuals, groups, organizations, and systems to respond productively to notable change without engaging in an extended period of regressive behaviour. Recently, there has been growing attention to the relationship between resilience and cities. To contribute to this stimulating debate, this paper first provides the theoretical framework and links the concept of resilience to urban studies. Subsequently, it enlightens, through a systems perspective and the aspect-based sentiment analysis (ABSA) methodology, the possibility to enrich the information variety endowment of urban policymakers, generated by new information units, to foster resilience capabilities in the urban context. Specifically, a large-scale text analysis study was conducted on the city of Rome to understand the sentiments expressed within the text generated online by citizens and visitors. The positive or negative sentiments linked to the hidden problems of the urban context were organized within collective perception-based maps for each of the analysed points of interest (POIs). Since cities represent complex decision-making contexts, this study aimed to outline a methodology and a tool that would help foster resilient thinking in urban policies by enriching the diversity of the information variety endowment of urban decision-makers.

Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised information. Existing algorithms of MS-UDA either only exploit the shared features, i.e., the domain-invariant information, or based on some weak assumption in NLP, e.g., smoothness assumption. To avoid these problems, we propose two transfer learning frameworks based on the multi-source domain adaptation methodology for SA by combining the source hypotheses to derive a good target hypothesis. The key feature of the first framework is a novel Weighting Scheme based Unsupervised Domain Adaptation framework ((WS-UDA), which combine the source classifiers to acquire pseudo labels for target instances directly. While the second framework is a Two-Stage Training based Unsupervised Domain Adaptation framework (2ST-UDA), which further exploits these pseudo labels to train a target private extractor. Importantly, the weights assigned to each source classifier are based on the relations between target instances and source domains, which measured by a discriminator through the adversarial training. Furthermore, through the same discriminator, we also fulfill the separation of shared features and private features.Experimental results on two SA datasets demonstrate the promising performance of our frameworks, which outperforms unsupervised state-of-the-art competitors.

Sentiment Analysis of Teachers Using Social Information in Educational Platform Environments

Learners’ opinions constitute an important source of information that can be useful to teachers and educational instructors in order to improve learning procedures and training activities. By analyzing learners’ actions and extracting data related to their learning behavior, educators can specify proper learning approaches to stimulate learners’ interest and contribute to constructive monitoring of learning progress during the course or to improve future courses. Learners-generated content and their feedback and comments can provide indicative information about the educational procedures that they attended and the training activities that they participated in. Educational systems must possess mechanisms to analyze learners’ comments and automatically specify their opinions and attitude towards the courses and the learning activities that are offered to them. This paper describes a Greek language sentiment analysis system that analyzes texts written in Greek language and generates feature vectors which together with classification algorithms give us the opportunity to classify Greek texts based on the personal opinion and the degree of satisfaction expressed. The sentiment analysis module has been integrated into the hybrid educational systems of the Greek school network that offers life-long learning courses. The module offers a wide range of possibilities to lecturers, policymakers and educational institutes that participate in the training procedure and offers life-long learning courses, to understand how their learners perceive learning activities and specify what aspects of the learning activities they liked and disliked. The experimental study show quite interesting results regarding the performance of the sentiment analysis methodology and the specification of users’ opinions and satisfaction. The feature analysis demonstrates interesting findings regarding the characteristics that provide indicative information for opinion analysis and embeddings combined with deep learning approaches yield satisfactory results.

HMTL: Heterogeneous Modality Transfer Learning for Audio-Visual Sentiment Analysis

Multimodal sentiment analysis is an extended approach to traditional language-based sentiment analysis, which uses other relevant modality data. Multimodal sentiment analysis usually applies visual, textual, and acoustic representations for sentiment prediction. Recently, various data fusion methodologies have been proposed for multimodal sentiment analysis. In most cases, textual modality plays a major role, and visual and acoustic modalities are used as auxiliary sources for multimodal sentiment analysis. However, in general multimedia such as video, text transcripts of an individual's speech are not provided. Research on an audio-visual sentiment analysis methodology that does not depend on text modality is essential for multimodal sentiment analysis in real-world industrial applications. Therefore, it is important to improve audio-visual sentiment analysis because it currently exhibits lower performance than multimodal sentiment analysis, including text modality. In this paper, we propose heterogeneous modality transfer learning (HMTL) to utilize the knowledge of aligned text data as a source modality in transfer learning to improve audio-visual sentiment analysis performance. Our approach uses a decoder and adversarial learning techniques to reduce the gap between the source and target modalities in the embedded space for multimodal representation. Our proposed methodology experimentally outperformed recent unimodal and bimodal audio-visual sentiment analysis achievements.

A hybrid sentiment analysis method for Turkish

This paper presents a hybrid methodology for Turkish sentiment analysis, which combines the lexicon-based and machine learning (ML)-based approaches. On the lexicon-based side, we use a sentiment dictionary that is extended with a synonyms lexicon. Besides this, we tackle the classification problem with three supervised classifiers, naive Bayes, support vector machines, and J48, on the ML side. Our hybrid methodology combines these two approaches by generating a new lexicon-based value according to our feature generation algorithm and feeds it as one of the features to machine learning classifiers. Despite the linguistic challenges caused by the morphological structure of Turkish, the experimental results show that it improves the accuracy by 7 % on average.

Differentiating users by language and location estimation in sentiment analisys of informal text during major public events

In recent years there has been intense work on the analysis of social media to support marketing campaigns. A proper methodology for sentiment analysis is a crucial asset in this regard. However, when monitoring major public events the behaviour or social media users may be strongly biased by punctual actions of the participating characters and the sense of group belonging, which is typically linked to specific geographical areas. In this paper, we present a solution combining a location prediction methodology with an unsupervised technique for sentiment analysis to assess automatically the engagement of social network users in different countries during an event with worldwide impact. As far as the authors know, this is the first time such techniques are jointly considered. We demonstrate that the technique is coherent with the intrinsic disposition of individual users to typical actions of the characters participating in the events, as well as with the sense of group belonging.

Detecting Potential Insider Threat: Analyzing Insiders’ Sentiment Exposed in Social Media

In the era of Internet of Things (IoT), impact of social media is increasing gradually. With the huge progress in the IoT device, insider threat is becoming much more dangerous. Trying to find what kind of people are in high risk for the organization, about one million of tweets were analyzed by sentiment analysis methodology. Dataset made by the web service “Sentiment140” was used to find possible malicious insider. Based on the analysis of the sentiment level, users with negative sentiments were classified by the criteria and then selected as possible malicious insiders according to the threat level. Machine learning algorithms in the open-sourced machine learning software “Weka (Waikato Environment for Knowledge Analysis)” were used to find the possible malicious insider. Decision Tree had the highest accuracy among supervised learning algorithms and K-Means had the highest accuracy among unsupervised learning. In addition, we extract the frequently used words from the topic modeling technique and then verified the analysis results by matching them to the information security compliance elements. These findings can contribute to achieve higher detection accuracy by combining individual’s characteristics to the previous studies such as analyzing system behavior.

Mining E-commerce Websites to Provide Efficient Methodology for Sentiment Analysis

Mining E-commerce Websites to Provide Efficient Methodology for Sentiment Analysis

A novel feature extraction methodology for sentiment analysis of product reviews

Feature extraction is one of the key steps for text sentiment analysis (SA), and the corresponding algorithms have important effect on the results. In the paper, a novel methodology is proposed to extract the feature for SA of product reviews. First, based on the diversified expression forms of product reviews, the generalized TF–IDF feature vectors are obtained by introducing the semantic similarity of synonyms. Then, in view of the different lengths of product reviews, the local patterns of the feature vectors are identified with OPSM biclustering algorithm. Finally, we improve PrefixSpan algorithm to detect the frequent and pseudo-consecutive phrases with high discriminative ability (namely FPCD phrases), which contain word-order information. Furthermore, some important factors, such as the separation and discriminative ability of words, are also employed to improve the discriminative ability of sentiment polarity. Based on the previous steps, the text feature vectors are extracted. A series of the experiment and comparison results indicate that the performance for SA on product review is greatly improved.

Measuring e-Commerce service quality from online customer review using sentiment analysis

The biggest e-Commerce challenge to understand their market is to chart their level of service quality according to customer perception. The opportunities to collect user perception through online user review is considered faster methodology than conducting direct sampling methodology. To understand the service quality level, sentiment analysis methodology is used to classify the reviews into positive and negative sentiment for five dimensions of electronic service quality (e-Servqual). As case study in this research, we use Tokopedia, one of the biggest e-Commerce service in Indonesia. We obtain the online review comments about Tokopedia service quality during several month observations. The Naïve Bayes classification methodology is applied for the reason of its high-level accuracy and support large data processing. The result revealed that personalization and reliability dimension required more attention because have high negative sentiment. Meanwhile, trust and web design dimension have high positive sentiments that means it has very good services. The responsiveness dimension have balance sentiment positive and negative.

Sentiment Analysis System for Arabic Articles News (SASAAN)

Sentiment analysis (also known as opinion mining) identifies and analyzes opinions and emotions in many domains (e.g.news, articles, product reviews, blogs, forum posts). Opinion mining is very important for companies, governments and every one interested to know opinion about special subject. This research discusses the problem of identifying opinion in Arabic news and Arabic articles. Most previous researches focused on extracting opinion from direct sentiments at the level of the article. Considering that an article contains large number of sentences, and some of these sentences may be about different topics and may be not opinion sentence, we propose a new methodology for sentiment analysis for Arabic articles. It starts with identifying opinion sentence related to the target of the article. Machine learning and Typed Dependency Relations (TDR) are used to identify the opinion sentences. Sentences that contain one word of high frequency nouns or adjectives are classified as target sentences. Then opinion lexicon is built using machine learning based on dataset that was collected from different domains (e.g. politics, economy, government, sports, and art). Three methods are used to identify opinion mining in articles. A method that depends on Opinion Lexicon achieved F-score of 62.8%. Machine learning (SVM) method achieved F-score 42.63%. whereas, our method that identifies opinion sentences that are related to the target of article then using opinion lexicon achieved the best results (F-score of 73.25%). So we recommended to identify opinion sentences that are related to the target of the article, then use the opinion lexiconto know the opinion.

Fusing audio, visual and textual clues for sentiment analysis from multimodal content

A huge number of videos are posted every day on social media platforms such as Facebook and YouTube. This makes the Internet an unlimited source of information. In the coming decades, coping with such information and mining useful knowledge from it will be an increasingly difficult task. In this paper, we propose a novel methodology for multimodal sentiment analysis, which consists in harvesting sentiments from Web videos by demonstrating a model that uses audio, visual and textual modalities as sources of information. We used both feature- and decision-level fusion methods to merge affective information extracted from multiple modalities. A thorough comparison with existing works in this area is carried out throughout the paper, which demonstrates the novelty of our approach. Preliminary comparative experiments with the YouTube dataset show that the proposed multimodal system achieves an accuracy of nearly 80%, outperforming all state-of-the-art systems by more than 20%.

Using Sentiment Analysis to Monitor Electoral Campaigns

In recent years, there has been an increasing attention in the literature on the possibility of analyzing social media as a useful complement to traditional off-line polls to monitor an electoral campaign. Some scholars claim that by doing so, we can also produce a forecast of the result. Relying on a proper methodology for sentiment analysis remains a crucial issue in this respect. In this work, we apply the supervised method proposed by Hopkins and King to analyze the voting intention of Twitter users in the United States (for the 2012 Presidential election) and Italy (for the two rounds of the centre-left 2012 primaries). This methodology presents two crucial advantages compared to traditionally employed alternatives: a better interpretation of the texts and more reliable aggregate results. Our analysis shows a remarkable ability of Twitter to “nowcast” as well as to forecast electoral results.

When Can Social Media Lead Financial Markets?

Social media analytics is showing promise for the prediction of financial markets. However, the true value of such data for trading is unclear due to a lack of consensus on which instruments can be predicted and how. Current approaches are based on the evaluation of message volumes and are typically assessed via retrospective (ex-post facto) evaluation of trading strategy returns. In this paper, we present instead a sentiment analysis methodology to quantify and statistically validate which assets could qualify for trading from social media analytics in an ex-ante configuration. We use sentiment analysis techniques and Information Theory measures to demonstrate that social media message sentiment can contain statistically-significant ex-ante information on the future prices of the S&P500 index and a limited set of stocks, in excess of what is achievable using solely message volumes.