Sentiment Analysis and Opinion Mining Research Papers (original) (raw)

Sentiment analysis deals with the computational treatment
of opinion, sentiment, and subjectivity in text, has attracted
a great deal of attention. Sentiment analysis has been
widely used across a wide range of domains in recent
years, such as information retrieval, question answering
systems and social network. This paper presents a new
method for improving the semantic knowledge base for
sentiment classification in social web applications. It
comprises the three steps. First, to identify sentiment
terms. Next, to provide the context information from
training corpus and ground this information to lexical
resources such as WordNet. This Work applies to a
transfer learning method called cross-domain sentiment
classification. In Sentiment Analysis, transfer learning can
be applied to transfer sentiment classification from one
domain to another or building a bridge between two
domains. This is achieved by learning the semantic
knowledge base across the different domains. A model
called AS_LDA is used for the sentiment classification.
The performance of the proposed system improves the
accuracy of the Sentiment Classifier to a significant extent.

- by
- •
- Sentiment Analysis and Opinion Mining

This paper presents and evaluates different computational models for review rating prediction. The models rely solely on star ratings from an annotated corpus of customer reviews of mobile apps that were collected from the Google Play Store in a related work. Fine-granular opinions and the classification of their sentiment orientation were already available. The models build upon them to make predictions based on their polarity. Predicting star ratings is of importance to the sentiment analysis community because it can better be understood how customers subjectively rate products. Rating them consistently with corresponding written reviews, however, remains a difficult task for automated predictors. This paper sheds new light in that direction.

La détection automatique du langage figuratif dans les réseaux sociaux est un sujet de recherche extrêmement actif principalement en raison de son importance pour améliorer les performances des systèmes d’analyse d’opinions. Pour la première fois, l’édition 2017 du Défi Fouille de Texte (DEFT) s’intéresse à l’influence du langage figuratif (en particulier l’ironie, le sarcasme et l’humour) dans l’analyse d’opinions à partir de tweets en français. Trois tâches de niveaux de complexité croissants ont été proposées aux participants : (T1) déterminer la polarité globale des tweets non figuratifs, (T2) déterminer si un tweet contient ou non du langage figuratif, et (T3) déterminer la polarité globale des tweets figuratifs et non figuratifs. Douze équipes ont participé à ce défi. Les meilleurs résultats, en macro f-mesure, sont de 0,650 pour (T1), 0,783 pour (T2) et 0,594 pour (T3). Ces résultats montrent clairement que l’usage du langage figuratif complique considérablement l’analyse d’opinions.

- by Jihen Karoui
- •
- Sentiment Analysis and Opinion Mining

Social Networking Sites such as twitter and Facebook is growing in large number thus allowing general masses to share views amongst each other regarding social, entertainment, political, marketing issues. However this heap of data is in unstructured format and thus cannot be used for identifying public opinions. This paper presents a methodological approach to extract meaningful data from popular microblogging website like twitter. The majority opinion state is investigated and realized on the basis of polarity of the words shared in communication. The timely identification of the dominated opinion of people can be useful and employed indiverse areas such as marketing of product, entertainment promotions etc. INTRODUCTION With the advancement in technology, communication has witnessed widened horizons. Thishas facilitated economical ways to communicate and connect with people across the world. The distance is no longer a factor for difficulties in communication, this is all attributed to social media and networking. Social media has provided a platform for exchange of ideas, views, and feelings around the world just by the help of internet hence decreasing the money spent on communication through letters, calls from landline, mobile phones etc. It has also made sharing of information, pictures, audios, videos effortless. Social networks provide individuals with an account to keep and manage. Nearly 10TB of data is generated and spread through these social networks which have attracted huge interests from the research community and industry and lots of useful information can be gathered from this huge data. The Sentiments that people express can be used for doing a lot of research in marketing, education and other famous industries due to which sentiment analysis came into existence. Sentiment analysis is a way of classifying the opinions that are mined using opinion mining in positive, negative and neutral statement of opinion holder. Sentiment analysis is developing exponentially with numerous emerging approaches targeting the recognition of sentiment, reflected in written language [1]. The main problem of data which is collected from social network is that it is in unstructured form which makes it difficult to identify public opinion. To our knowledge the data gathered from social media and analyzed does not take dominated views into consideration In our paper we would be extracting useful data from a microblogging site like Twitter as it is open and people only use it to express their views only by the use of 140 characters per post then we would be finding out the sentiments of those opinions by the use of code developed in python and then provide the overall opinion of public about a topic.

- by Dr. Sandeep Kumar
- •
- Information Systems, Data Mining, Sentiment Analysis, Social Media

From outrage at corporations to excitement about innovations, marketplace sentiments are powerful forces in consumer culture that transform markets. This article develops a preliminary theory of marketplace sentiments. Defined as collectively shared emotional dispositions, sentiments can be grouped into three function-based categories: contempt for villains, concern for victims, and celebration of heroes. Marketplace actors such as activists, brands, and consumers have a variety of motives and methods for producing and reproducing sentiments. Activists plant, amplify, and hyper-perform sentiments to recruit consumers and discipline institutions. Brands carefully select, calibrate, and broadcast sentiments to entertain consumers and promote products. Consumers learn, experience, and communicate sentiments to commune and individuate in society. The emergent theory of marketplace sentiments (1) advances a sociocultural perspective on consumer emotion, (2) elevates the theoretical significance of emotional observations in cultural studies, (3) offers a sentiment-based understanding of the power of ideology, (4) indicates how activist sentiments can paradoxically benefit from brand cooptation, and (5) calls for human input in big data sentiment analysis. More broadly, the article proposes that cultures are systems of discourses, sentiments, and practices wherein discourses legitimize sentiments and practices, sentiments energize discourses and practices, and practices materialize discourses and sentiments.

- by Ahir Gopaldas
- •
- Public Opinion, Sentiment Analysis, Public Opinion Research, Investor Sentiment

The Movie reviews and ratings are used by the people to decide which movie to buy or watch. Movie reviews are used as a recommendation, on whether it's worth spending time and money to watch or buy a movie. Reviews contain both positive and negative opinion on the movie. Ratings are calculated based on the total positive reviews of the movie. Therefore it is important to identify whether the given review is a positive or negative. In this paper we have used movie review dataset (aclimdb) to train our machine and logistic regression algorithm which is used to predict the polarity of a given movie review. Introduction Decision making place an important role in human life, a good and correct decision will make our life better. Decisions can made based on others opinions. Manual efforts on thinking and wasting time in taking decisions are decreased. In case of deciding on which movie to buy or watch, people look at websites, which provides reviews and ratings of the movies. This makes people to decide on which movie to buy or watch. People may have good or bad opinion about the movie, they express there opinion through reviews in the websites like amazon, BookMyShow etc. Where people look at the reviews and ratings to decide which movie to watch or buy. Good opinions about the movies are classified as positive and bad opinions are classified as negative. Review containing "good", "wonderful", "enjoyed" like keywords are called as positive. Review containing "not nice", "bad" like keywords are called as negative. Movie ratings are calculated based on the positive opinion about the movie. Sentiment analysis is a technique used to classify positive and negative opinion of the movie review. Where sentiment analysis is text classification tool, which analyses the text and identifies the polarity of the text.

The rapid advancement of web technology has led to an exponential increase in the volume of data present online for internet users. Travellers book their hotels only after extensive scrutinisation of hotel reviews on online websites. Hence, it is an absolute necessity for hotel's management board to gain insights from customer reviews and feedbacks to improve upon their services for a better customer satisfaction index. This research explores the use of Artificial Neural Networks (ANN) powered by Google's Word2Vec skip-gram algorithm for customer sentiment analysis and review classification. The proposed model achieves a high test accuracy of 0.9248, with an average F1-Score of 0.925. Unsupervised sentiment clustering effectively classifies the reviews into four distinct categories and enables the Hotel Management to work out the major problems experienced by the customers.

The automobile industry is currently looking at the technology needed to move from today's original autonomous autos to a self-contained and safe driving solution. The automobile industry has been remarkably successful in producing reliable, safe, and affordable cars over the past century. Due to the significant progress made in computers and telecommunications, an autonomous car became a reality. In this regard, an android driver-less car is a vehicle that uses a combination of motors, software, and sensors to park cars between destinations without a human operator. To be fully autonomous, vehicles must be able to travel unmanned to a predetermined destination on roads that are not fit for use. In this paper, the android controlled Arduino based intelligent car parking development stages and functionalities has been discussed. The motor system will be composed of the dc motors that run the car as well as the wheels and body of the car. The DC motor controls the circuit and a software driver. The android application will drive the car forward, reverse, left, and right (stopping will be the absence of a forward or backward command). It will do this by means of the software driver. There is also one motor which holds the brake and release. The significance of this system is that it has a distinctiveness to control real cars in real-time with android applications including steering control, gear shifting, horn control, and engine on/off. It has a self-parking system in a narrow crowded system through the sensors reading the environment and with actuators, a car could be park itself. Finally, on enabling effective automobile safety and efficient automotive cars, some of the challenges are needed to be addressed (and to provide) useful suggestions for approval by car manufacturers, designers, policymakers, and regulatory bodies.

Academic industries used to collect feedback from the students on the main aspects of course such as preparations, contents, delivery methods, punctual, skills, appreciation, and learning experience. The feedback is collected in terms of both qualitative and quantitative scores. Recent approaches for feedback mining use manual methods and it focus mostly on the quantitative comments. So the evaluation cannot be made through deeper analysis. In this paper, we develop a student feedback mining system (SFMS) which applies text analytics and sentiment analysis approach to provide instructors a quantified and deeper analysis of the qualitative feedback from students that will improve the students learning experience. We have collected feedback from the students and then text processing is done to clean the data. Features or topics are extracted from the pre-processed document. Feedback comments about each topic are collected and made as a cluster. Classify the comments using sentiment classifier and apply the visualization techniques to represent the views of students. This proposed system is an efficient approach for providing qualitative feedback for the instructor that enriches the students learning.

- by R. MENAHA
- •
- Sentiment Analysis and Opinion Mining

Our study employs sentiment analysis to evaluate the compatibility of Amazon.com reviews with their corresponding ratings. Sentiment analysis is the task of identifying and classifying the sentiment expressed in a piece of text as being positive or negative. On e-commerce websites such as Amazon.com, consumers can submit their reviews along with a specific polarity rating. In some instances, there is a mismatch between the review and the rating. To identify the reviews with mismatched ratings we performed sentiment analysis using deep learning on Amazon.com product review data. Product reviews were converted to vectors using paragraph vector, which then was used to train a recurrent neural network with gated recurrent unit. Our model incorporated both semantic relationship of review text and product information. We also developed a web service application that predicts the rating score for a submitted review using the trained model and if there is a mismatch between predicted rating score and submitted rating score, it provides feedback to the reviewer.

In recent years, there are massive numbers of users who share their contents over wide range of social networks. Thus, a huge volume of electronic data is available on the Internet containing the users' thoughts, attitudes, views and opinions towards certain products, events, news or any interesting topics. Therefore, sentiment analysis becomes a desirable topic in order to automate the process of extracting the user's opinions. One of the widely content sharing languages over the social network is Arabic Language. However Arabic language has several obstacles that make the sentiment analysis a challenging problem. Most users share their contents in informal Arabic. Additionally, there are lots of different Arabic dialects. Hence, Arabic sentiment analysis researches is developed slowly compared to other languages such as English. This paper proposes a new hybrid lexicon approach for Arabic sentiment analysis that combines in the same framework both unsupervised and supervised technique. In the unsupervised phase, the polarity of data is extracted by means of Look-up table stemming technique. In the supervised phase, we use the data of the true classified polarity from the unsupervised phase to generate and train a classifier for the further classification of the unclassified data. We test and evaluate the proposed approach using MIKA corpus [1]. The results show that the proposed approach gives better results.

On today's fast spreading use of social media, many websites have offer reviews of items like books, cars, mobiles, movies etc. They describe the product in some detail and evaluate them as good/bad, preferred/not preferred, so it is necessary to categorize these reviews in an automated way. Sentiment analysis is one kind of computational technique of Artificial Intelligence. It is the task of identifying positive and negative opinions, emotions, and evaluations. This article represents Sentiment analysis, it's issues, applications and some of the methods used to evaluate the review using sentiment analysis.

The aim of the study is to provide an insight into sentiment analysis as a social media monitoring tool with its limits and potential. Practical application of this selected topic takes the form of a complex analysis of 720 Facebook posts with a total of 59 967 comments in order to determine the success of respective chain stores communication and provide an evaluation of types of marketing communication mix tools they are using and customers´attitudes towards this communication. The study offers an insight into this popular form of brand´s communication with customers in case of eight most common grocery chain stores in Slovakia.

- by Magdalena Kacaniova and +1
- •
- Marketing, Digital Media, Advertising, Sentiment Analysis

Product reviews are becoming increasingly useful. In this paper, Twitter has been chosen as a platform for opinion mining in trading strategy with Mubasher products, which is a leading stock analysis software provider in the Gulf region. This experiment proposes a model for sentiment analysis of Saudi Arabic (standard and Arabian Gulf dialect) tweets to extract feedback from Mubasher products. A hybrid of natural language processing and machine learning approaches on building models are used to classify tweets according to their sentiment polarity into one of the classes positive, negative and neutral. In addition, Regarding to the comparison between SVM and Bayesian method, we have split the data into two independents subsets form different periods and the experiments were carried out for each subsets respectively in order to distinction between positive and negative examples by using neutral training examples in learning facilitates. Similar result has been given.

We report results of a comparison of the accuracy of crowdworkers and seven Natural Language Processing (NLP) toolkits in solving two important NLP tasks, named-entity recognition (NER) and entity-level sentiment (ELS) analysis. We here focus on a challenging dataset, 1,000 political tweets that were collected during the U.S. presidential primary election in February 2016. Each tweet refers to at least one of four presidential candidates, i.e., four named entities. The groundtruth, established by experts in political communication , has entity-level sentiment information for each candidate mentioned in the tweet. We tested several commercial and open source tools. Our experiments show that, for our dataset of political tweets, the most accurate NER system, Google Cloud NL, performed almost on par with crowdworkers, but the most accurate ELS analysis system, TensiStrength, did not match the accuracy of crowdworkers by a large margin of more than 30 percent points.

The social media is gaining a lot of importance among businesshouses, academicians, medical practitioners, politicians, among others, due to its role in creating awareness about products, services, and socio-political views. The end users of these products, services, and views provide their feedbacks in the form of comments. An accurate determination of the sentiments of end users is crucial in designing policies and plans for products and services in future. As the processing power and storage capacities of computers have increased several folds, researchers can focus more on the accuracy of sentiment detection than consumption of computational resources. In this paper, we are applying a set of heuristics to analyse sentiments using freely available dictionary resources and open source tools. We have tested these heuristics over a large data set collected from standard sources. The experimental results are promising and opening new research directions in dictionary-based sentiment analysis.

Social media applications such as twitter, face book, blogs etc are used by the people extensively to give their opinions on everything. Study on these opinions is the major research trend and this research will help to understand the people views and this study will help to take further decisions. For the study of exploring the opinion, NLP and ML is used to classify the different emotions such as positive, negative and neutral opinions. It is very complex task to examine the input text data given by the user in social media applications. Here proposed a novel bounded logistic regression with the demonetization data sets taken from different cities of India. Results of the approached technique give the good accuracy. INTRODUCTION With the extensive use of social applications for communications, people across the globe create tons of text data every day. An interaction usually happens through a public domain, and making all this data available to everyone. Analysis of emotions is the process to extract the opinions from social media applications. Location wise data is collected and opinions of users are analyzed to find out the location wise impact of any product or any scheme. Result analyses are helpful for taking optimal decisions in future. Here, Data is collected from different locations based on the demonetization scheme and used the bounded logistic regression method and categorize the opinions of the people. Twitter Data set on demonetization took from different locations of India and explored the sentiments from that data set. In this paper, exploring the emotions and analysis of those location inference system that works with dataset from Twitter , which restricts the posts to 200 characters, and taken recent tweets only and extracting the information and process of identifying the emotions that the people express in the form textual reviews later categorized as positive, negative or neutral. Analysis of emotions is very complex and crucial in the growth of the company. This process will provide the useful information about the reviews. Demonetization scheme was launched in the year of 2016 November 8 and decision took by the Indian government. Twitter application is majorly used by the people to interact and express their feelings in the form of text. Share the post with someone is known as tweeting. Users are very curious to find out the tweets of their interest [1]. This manuscript is defined as follows: section II is about the earlier work and proposed method, section III is about the implementation and results from the proposed technique, section IV is conclusion and future work.

In this paper we propose a fully unsupervised approach for product aspect discovery in on-line consumer reviews. We apply a two-step hierarchical clustering process in which we first cluster words representing aspects based on the semantic similarity of their contexts and then on the similarity of the hypernyms of the cluster members. Our approach also includes a method for assigning class labels to each of the clusters. We evaluated our methods on large datasets of restaurant and camera reviews and found that the two-step clustering process performed better than a single-step clustering process at identifying aspects and words refering to aspects. Finally, we compare our method to a state-of-the-art topic modelling approach by Titov and McDonald, and demonstrate better results on both datasets.

I present a tool which tells the quality of document or its usefulness based on annotations. Annotation may include comments, notes, observation, highlights, underline, explanation, question or help etc. comments are used for evaluative purpose while others are used for summarization or for expansion also. Further these comments may be on another annotation. Such annotations are referred as meta-annotation. All annotation may not get equal weightage. My tool considered highlights, underline as well as comments to infer the collective sentiment of annotators. Collective sentiments of annotators are classified as positive, negative, objectivity. My tool computes collective sentiment of annotations in two manners. It counts all the annotation present on the documents as well as it also computes sentiment scores of all annotation which
includes comments to obtain the collective sentiments about the document or to judge the quality of document. I demonstrate the use of tool on research paper.

In recent years, the rapid growth of the Internet has changed the way people interact globally. The internet usage is quite diverse, which one of them is a media to collect user generated content, including online review. Public sentiment is cumulative of people's arguments and opinions about the issues on public community. The sentiment could be expressed as positive or negative. One of online review type is the online forum, which contain specific topic that can affect people's opinion in related discussions. This study aim to show how to measure polarity of public sentiment using machine learning principle. Even though this idea can be applied generally to any public domain, we choose business case study in telecommunication industry concerning their service level to the customer. We collect data from Kaskus, which is the most popular online forum in Indonesia. The interactions between users and their affection regarding the topic is measured. We use sentiment analysis based on naïve bayes classifier and word cloud approach in Bahasa to support the research objective.

After an earthquake, it is necessary to understand its impact to provide relief and plan recovery. Social media (SM) and crowdsourcing platforms have recently become valuable tools for quickly collecting large amounts of first-hand data after a disaster. Earthquakerelated studies propose using data mining and natural language processing (NLP) for damage detection and emergency response assessment. Using tex-data provided by the Euro-Mediterranean Seismological Centre (EMSC) collected through the LastQuake app for the Aegean Earthquake, we undertake a sentiment and topic analysis according to the intensities reported by their users in the Modified Mercalli Intensity (MMI) scale. There were collected 2,518 comments, reporting intensities from I to X being the most frequent intensity reported III. We use supervised classification according to a rule-set defined by authors and a two-tailed Pearson correlation to find statistical relationships between intensities reported in the MMI by LastQuake app users, polarities, and topics addressed in their comments. The most frequent word among comments was: "Felt." The sentiment analysis (SA) indicates that the positive polarity prevails in the comments associated with the lowest intensities reported: (I-II), while the negative polarity in the comments is associated with higher intensities (III-VIII and X). The correlation analysis identifies a negative correlation between the increase in the reported MMI intensity and the comments with positive polarity. The most addressed topic in the comments from LastQuake app users was intensity, followed by seismic information, solidarity messages, emergency response, unrelated topics, building damages, tsunami effects, preparedness, and geotechnical effects. Intensities reported in the MMI are significantly and negatively correlated with the number of topics addressed in comments. Positive polarity decreases with the soar in the reported intensity in MMI demonstrated the validity of our first hypothesis, despite not finding a correlation with negative polarity. Instead, we could not prove that building damage, geotechnical effects, lifelines affected, and tsunami effects were topis addressed only in comments reporting the highest intensities in the MMI.

- by R MENAHA
- •
- Sentiment Analysis and Opinion Mining

Sentiment Analysis is a channel by which automated feedback analysis can be processed effectively and efficiently. The reviews reachable are not only useful for customers buying a product or service but also the manufacturers and industrialists to formulate their production and marketing strategies as well as government organizations to access the views of the citizens. Recommender systems, market researches, and predictions on various social media platforms can be made more practical and comprehensive by sentiment analysis. It has evolved in numerous ways starting from the coarsely grained analysis. But when we need to find intricate details scrunched into a single statement or so, aspect-level sentiment analysis is the way. The uprising of deep learning approaches has opened doors in various applications, including Aspect-based Sentiment Analysis. These networks are computationally strong and can be trained easily. However, since they lag in recognizing semantic complexities, various Natural Language Processing techniques have been joined into the neural models. Researchers have been creative with inventing various novel models, combining a myriad of neural networks and attention mechanisms to improve aspect detection and sentiment polarity identification. The promise that this field provides because of its independent nature compels scientists to delve into the topic. In this work, fine grained analysis is not only processed for the aspect and aspect word detection but also for polarity and its intensity analysis. Our Contributions include the enriched input embedding with token, orientation, grammatical function, field and intensity components in the embedding stage, refined pattern extraction with convolutional kernels and improved performance using attention mechanism in the latter stages. Our experimental results reveal that, our procedural methodology has brought out an optimal enhanced performance compared to the near closer designs.

Opinion target extraction or aspect extraction is the most important subtask of the aspect-based sentiment analysis. This task focuses on the identification of the targets of user's opinions or sentiments from online reviews. In the recent years, syntactic patterns-based approaches have performed quite well and produced significant improvement in the aspect extraction task. However, these approaches are heavily dependent on the dependency parsers which produced syntactic relations following the grammatical rules and language constraints. In contemporary, users do not give much importance to these rules and constraints while expressing their opinions about particular product and neither reviewer websites restrict users to do so. This makes syntactic patterns-based approaches vulnerable. Therefore, in this paper, we are proposing a twofold rules-based model (TF-RBM) which uses rules defined on the basis of sequential patterns mined from customer reviews. The first fold extracts aspects associated with domain independent opinions and the second fold extracts aspects associated with domain dependent opinions. We have also applied frequency-and similarity-based approaches to improve the aspect extraction accuracy of the proposed model. Our experimental evaluation has shown better results as compared with the state-of-the-art and most recent approaches.

Opinion Mining is a process of automatic extraction of knowledge from the opinion of others about some
particular topic or problem. The idea of Opinion mining and Sentiment Analysis tool is to “process a set
of search results for a given item, generating a list of product attributes (quality, features etc.) and
aggregating opinion”. But with the passage of time more interesting applications and developments
came into existence in this area and now its main goal is to make computer able to recognize and
generate emotions like human. This paper will try to focus on the basic definitions of Opinion Mining,
analysis of linguistic resources required for Opinion Mining, few machine learning techniques on the
basis of their usage and importance for the analysis, evaluation of Sentiment classifications and its
various applications.

- by Padmaja S and +2
- •
- Mining Engineering, Data Mining, Web Mining, Sentiment Analysis

We report results of a comparison of the accuracy of crowdworkers and seven Natural Language Processing (NLP) toolkits in solving two important NLP tasks, named-entity recognition (NER) and entity-level sentiment (ELS) analysis. We here focus on a challenging dataset, 1,000 political tweets that were collected during the U.S. presidential primary election in February 2016. Each tweet refers to at least one of four presidential candidates, i.e., four named entities. The groundtruth, established by experts in political communication, has entity-level sentiment information for each candidate mentioned in the tweet. We tested several commercial and open-source tools. Our experiments show that, for our dataset of political tweets, the most accurate NER system, Google Cloud NL, performed almost on par with crowdworkers, but the most accurate ELS analysis system, TensiStrength, did not match the accuracy of crowdworkers by a large margin of more than 30 percent points.

Menoume Evropi Campaign & GRinEuro Brandwach Social Media Monitoring & Sentiment Analysis Data

- by Hamed Rubaiee
- •
- Sentiment Analysis, Saudi Arabia, Applications of Machine Learning, Twitter
- by Taha Khan
- •
- Machine Learning, Educational Data Mining, Pedagogics, Computer Programing Languages

In un panorama scolastico nel quale le tecnologie digitali riescono raramente a trovare il giusto spazio e l’attenzione per essere trattate in modo approfondito, strutturato ed efficace, è difficile pensare di poter trasmettere agli studenti vere e proprie competenze. In assenza di una disciplina che sia in grado di rispecchiare la complessità di un reale in continua trasformazione, si rivela più praticabile elicitare le loro attitudini, generando curiosità e permettendo loro di conoscere nuovi settori lavorativi e nuovi ambiti di studio. Dopo una breve introduzione alla metodologia didattica in grado di concretizzare questa proposta, il digital authentic learning, il contributo dimostra come la tone analysis possa arricchire l’attività di lettura critica del testo e avvicinare gli studenti alle nuove frontiere dell’intelligenza artificiale.

- by Alessandro Iannella
- •
- Artificial Intelligence, Latin Literature, Education, Educational Technology

In a wide range of applications, solving the linear system of equations Ax = b is appeared. One of the best methods to solve the large sparse asymmetric linear systems is the simplified generalized minimal residual (SGMRES(m)) method. Also, some improved versions of SGMRES(m) exist: SGMRES-E(m, k) and SGMRES-DR(m, k). In this paper, an intelligent heuristic method for accelerating the convergence of three methods SGMRES(m), SGMRES-E(m, k), and SGMRES-DR(m, k) is proposed. The numerical results obtained from implementation of the proposed approach on several University of Florida standard matrixes confirm the efficiency of the proposed method.

The object of this research consists of the examination of the pro- Eurozone grassroots advocacy network movement known as the “Whistle Movement” that has emerged in Greece and advocated in favour of Greece Eurozone membership and became a constituent part of the “Yes” election “Committee” during the Greek 2015 referendum. It will be evaluated as a grassroots advocacy network movement having the characteristics of a “Crowd-Enable Connective Action”.
The studied period spans from 1st of May 2015 to the 6th of July 2015, and includes the first signs of pro Eurozone citizens engagement into communicative action to demonstrate their antithesis against the precarious Governmental negotiation tactics and response to the EU bailout proposals and later the emergence of different forms of campaigning (digital campaigning, traditional canvassing and Get Out the Vote) as well as different forms of mobilisation (demonstrations, occupying the ”Syntagma” Constitution Square). The focus was placed on the forms of political participation and the transformation of the actors’ consciousness in relation to their participation and experience, in connection with (1) the objective conditions; (2) their own political orientation beliefs, ideas and ideals (3) their own conceptualization of “patriotism” and (4) their own identification of which issue was at stake.
The emergence and spreading of the new forms of activist political participation have been given special attention. Further special attention has been given to the factors differentiating firstly grassroots issue advocacy networks from traditional social movements. Methodologically, this research focuses on three key points. The first concerns the theoretical context of social movements, networked advocacy and political activism respective literature and its relevance to the Greek case and what are their qualitative differentiating characteristics. The second point concerns the specific study of this particular grassroots issue advocacy network in Greece and focuses on using in-depth, semi- structured interviews to explore political activists’ views in relation firstly to its formation raison d’etre, secondly in relation to its effectiveness, thirdly in relation to its organisational structure and form and fourthly in relation to its political footprint and legacy. The third point concerns the measurement and evaluation of the digital campaign run by the movement through computational Social Media Monitoring and Sentiment Analysis. The choice of the interview participants provided the opportunity to investigate the forms and the effects of issue advocacy campaigning according to the participants own recollections and evaluations. The criterion has been to interview people who actively participated in the formation of this movement and the running of its issue advocacy campaign.

Nowadays, internet has changed the world into a global village. Social Media has reduced the gaps among the individuals. Previously communication was a time consuming and expensive task between the people. Social Media has earned fame because it is a cheaper and faster communication provider. Besides, social media has allowed us to reduce the gaps of physical distance, it also generates and preserves huge amount of data. The data are very valuable and it presents association degree between people and their opinions.
The comprehensive analysis of the methods which are used on user behavior prediction is presented in this paper. This comparison will provide a detailed information, pros and cons in the domain of sentiment and opinion mining.

Decision making both on individual and organizational level is always accompanied by the search of other’s opinion on the same. With tremendous establishment of opinion rich resources like, reviews, forum discussions, blogs, micro-blogs, Twitter etc provide a rich anthology of sentiments. This user generated content can serve as a benefaction to market if the semantic orientations are deliberated. Opinion mining and sentiment analysis are the formalization for studying and construing opinions and sentiments. The digital ecosystem has itself paved way for use of huge volume of opinionated data recorded. This paper is an attempt to review and evaluate the various techniques used for opinion and sentiment analysis.