Piece Of Text Research Articles

Aspect-Based Sentiment Analysis Using a Hybridized Approach Based on CNN and GA

Sentiment analysis is a computational analysis of unstructured textual data, used to assess the person's attitude from a piece of text. Aspect-based sentimental analysis defines the relationship among opinion targets of a document and the polarity values corresponding to them. Since aspects are often implicit, it is an extremely challenging task to spot them and calculate their respective polarity. In recent years, several methods, strategies and improvements have been suggested to address these problems at various levels, including corpus or lexicon-based approaches, term frequency and reverse document frequency approaches. These strategies are quite effective when aspects are correlated with predefined groups and may struggle when low-frequency aspects are involved. In terms of accuracy, heuristic approaches are stronger than frequency and lexicon based approaches, however, they consume time due to different combinations of features. This article presents an effective method to analyze the sentiments by integrating three operations: (a) Mining semantic features (b) Transformation of extracted corpus using Word2vec (c) Implementation of CNN for the mining of opinion. The hyperparameters of CNN are tuned with Genetic Algorithm (GA). Experimental results revealed that the proposed technique gave better results than the state-of-the-art techniques with 95.5% accuracy rate, 94.3% precision rate, 91.1% recall and 96.0% f-measure rate.

Topic-Enhanced Capsule Network for Multi-Label Emotion Classification

Identifying multiple emotions in a piece of text is an important research topic in the NLP community.Existing methods usually model the task as a multi-label classification problem, while these work has two issues. First, these methods fail to leverage the topic information of the text, which has been shown to be effective for sentiment analysis task. Second, different parts of the text can contribute differently to predicting different emotion labels, so the proposed model needs to capture effective features for each corresponding emotion, which is not considered by existing models. To tackle these problems, we propose a topic-enhanced capsule network, which contains two main parts: a variational autoencoder and a capsule module, for multi-label emotion detection task. Specifically, the variational autoencoder can learn the latent topic information of the text, and the capsule module can capture rich features for corresponding emotion. Experimental results on two benchmark datasets show that the proposed model achieves the current best performance, outperforming previous methods and strong baselines by a large margin.

Deep Text Summarization using Generative Adversarial Networks in Indian Languages

Abstractive Text Summarization (ATS) is a task of capturing information from different sources and condense it such that, content is represented well and there is no loss of information. It has been an active area of research for quiet sometime now. ATS is more closer to human generated summaries and have the capability of representing and combining multiple information. With advent of deep learning architectures, many tasks relating to natural language processing have achieved persistent and comparable high performances. It has proven advantageous and showed promising results in machine translation, speech recognition, image captioning and many others using sequence to sequence models. Language tools such as Part of Speech taggers, Named Entity Recognizer for Indian languages are not very competitive and hence, language specific techniques do not perform very well for Indian languages. Deep learning techniques are language agnostic and hence can overcome these shortcomings. In this paper, Generative Adversarial Networks(GAN(s)) are assimilated to create gist for longer piece of text in conjunction to paraphrase detection.

Design and Evaluation of WriteBetter: A Corpus-Based Writing Assistant

Corpus-based writing assistants are aimed to show how words are used in real context: they provide word use examples from which users can (1) draw inspiration for their writing and (2) understand how words are used together to improve their own writing. Although the idea of integrating a corpus-based writing assistant (concordancer) into word processors is not new, their integration is designed to be not as straightforward as writing in a word processor. In this paper, we present WriteBetter, a corpus-based writing assistant designed to be integrated into Microsoft Word, Google Docs, and Overleaf. This integration makes its use straightforward and easy as users can see corpus-based examples (1) in real-time while writing in the word processor or (2) just selecting a piece of text in their document. This facilitates user-corpus interaction as the required user's interaction is minimal. After contextualising the state of the art regarding the benefits of corpus-consultation, we discuss the design features of WriteBetter that make it novel in relation to other tools. Next, we present a user evaluation of the first version of WriteBetter, which was carried out on 11 undergraduate students of a Chilean university, who were asked to trial the software while writing in English. Based on this evaluation, we designed a new version of WriteBetter, which was further evaluated online on 36 users. WriteBetter is now available for everyone as SaaS.

The Recycling of News in Swedish Newspapers: Reused quotations and reports in articles about the crisis in the Swedish Academy in 2018

Abstract Newspapers in Sweden are experiencing reduced revenues due to decreases in advertisement sales and reader subscriptions. Given such circumstances, one way of being more cost-effective is for journalists to recycle pieces of texts already published by others. In this article, I investigate to what extent and how the four biggest newspapers in Sweden do this. Following a close reading of 120 articles about the crisis in the Swedish Academy in 2018, I found that the newspapers included recycled quotations attributed to other media to a great extent. Moreover, recycled statements from other media were often intermingled with quotes from new interviews; however, social media were not used as sources very often. A discussion of the problematic aspects of “a culture of self-referentiality” concludes the article.

Online Social Networks and Writing Styles–A Review of the Multidisciplinary Literature

In recent years, author identification has become an active research area, where the major differences are caused by paper or online medium, mode of entry and target audience. Much research has been devoted to analyzing writing styles in handwritten, word-processed and online social networks (OSN) texts. Word processing editors that typically include spell and grammar checkers may influence the writing style as it allows an individual to edit a piece of text to perfection. Thus, similarities may exist between OSN and word-processed texts. Moreover, none of the studies to date have made a detailed comparison of the writing styles across multidisciplinary factors. This paper attempts to close the gap between the writing styles in pre- and post-Internet periods as well as provide an in-depth comparison of the writing styles in OSN texts across three major factors: demographics, personality & behavior, and cybersecurity. The aim is to learn from past literature as we advance these techniques to OSN texts. Thus, in this paper, we also propose a novel machine learning prediction model based on tense morphology, to classify age and gender from English blogs, and the PAN 2013 dataset. This model achieves an accuracy of 94%-98% and 95%-97% for age and gender, respectively.

Named Entities and Their Role in Creating Context Information.

Context encompasses the classification of a certain environment by its key attributes that take the role of semantic markers. It is an abstract representation of a certain data environment. In texts, the context classifies and represents a piece of text in a generalized form. Context can be a recursive construct when summarizing information on a more coarse-grained level. This paper presents identification and standardization of context on different levels of granularity that finally supports faster and more precise information retrieval. The prototypical system presented here applies supervised learning for a semi-automatic approach to extract, distil, and standardize data from text. The approach is based on named-entity recognition and simple ontologies for identification and disambiguation of context. Even though the prototype shown here still represents work in progress, it already demonstrates its potential for mining texts on different levels of context granularity. The paper presents the design of the Contexter system that supports identification and classification of misinformation and fake news around the topic Covid-19.

Textual Typologies Produced by Students by Transforming an Artistic Sign as Learning Indication

This study uses the transcoding process of visual perceptions of an image to written language in order to monitor the learning of physics concepts. Through this procedure, high school students were asked to write a piece of text that interprets an artistic work from possible connotative readings that associate it to the content taught. In addition to the scientific content domain by the learner, the discursive organization employed in the text is also examined. The discursive organization is based on descriptive, narrative and discursive typologies. In that sequence, they form an increasingly complex composing structure. The study starts from the assumption that the appropriation of the content taught tends to keep a correlation with the typological development used while constructing the text. Results indicate that dissertation organizations tend to indicate better understanding of the content when compared to narratives or descriptions. Thus, the study suggests considering text typology as a complementary tool to assess the learner’s understanding of the taught content.

Вербальна об’єктивація концептів „FAILURE” і „НЕВДАЧА” в творах сучасної американської та української художньої літератури: перцептивно-когнітивний та регулятивний аспекти

The article describes the features of the perception-cognitive and regulation macrostructure components of the FAILURE and НЕВДАЧА concepts in the epidigmatic plane on the basis of the text pieces selected from modern American and Ukrainian fiction. The analysis of these components of the concepts under consideration is carried out in the framework of the semantic cognitive approach by performing the cognitive interpretation procedure of the text pieces, the results of which have been used for formulating semantic cognitive features that constitute the perception-cognitive and regulation layers of the concept. The specificity of the regulatory aspect of understanding the essence of failure by the bearers of American and Ukrainian linguistic consciousness is clarified due to the semantic cognitive features that structure the regulatory zone of the concept macrostructure and update the strategies of the value and target block of the individual in the context of failure. It has been found that in the epidigmatic plane, in the process of conceptualizing failure by American and Ukrainian speakers, perceptual receptors dominate cognitive-mental thought projections. The visual analyzer is the most effective for the bearers of the American and Ukrainian linguistic consciousness in the context of sensory reflection of the failure category, the sound, taste, smell and tactile receptors are less effective. Cognitive subcomponents of the FAILURE and НЕВДАЧА concepts are structured due to vital and floromorphic metaphorical images; zoomorphic and aeromorphic images for the FAILURE concept as well as religious, aquamorphic and subject images for the НЕВДАЧА concept are considered nationally specific. The regulation zone of the FAILURE concept is significantly larger than the similar НЕВДАЧА concept zone, so for Ukrainian speakers rules and guidelines that help regulate areas covering the conceptual nature of failure are more important in understanding the failed outcome of action than for American ones.

Deep Learning based Sentiment Analysis for Social Media Network

Sentiment Analysis is the process of identifying opinions expressed in a piece of text. It determines whether the writer's attitude towards a product is positive, negative, or neutral. Sentiment evaluation addresses such need by way of detecting evaluations on the social media textual content. Product evaluations are valuable for upcoming shoppers in supporting them make choices. In recent, deep learning is loom as a powerful manner for fixing sentiment classification troubles. The neural network intrinsically learns a beneficial representation without the efforts of human. This paper presents the overall performance evaluations of deep learning classifiers for big-scale sentiment evaluation. In this system the reviews from the online shopping website called flipkart.com is analyzed and divided as positive, negative and neutral by Multilayer Perceptron (MLP) Neural Network depending on the aspect of the product. The proposed work is simulated by using SPYDER. In our system the accuracy, precision, F-measure and recall is calculated for Multilayer Perceptron (MLP) Neural Network, Random Forest and Support Vector Machine (SVM) algorithm. During comparison Multilayer Perceptron (MLP) Neural Network gives the best accuracy of 99% than other two algorithms.

Strategies for Marketing Really New Products to the Mass Market: A Text Mining-Based Case Study of Virtual Reality Games

This paper reports on a text mining-based case study aimed at determining how virtual reality (VR) games, as examples of really new products (RNPs), market themselves when they are introduced to the mass market. The goal was to examine the marketing foci of RNPs and any subsequent changes over time when the RNPs survive. VR games are a type of RNP offering several unique benefits, such as immersive gameplay and storytelling, which are advanced compared with their earlier counterparts. To examine the marketing foci of VR games, we collected 17,000 pieces of promotional text from a major online gaming marketplace, Steam Store, published from the beginning of the second quarter of 2016 to the third quarter of 2018. We performed text analysis (topic modeling) and found that game marketers paid particular attention to the VR nature of VR games when they first entered the marketplace. However, game content increasingly was emphasized in subsequent quarters. In addition, the marketing foci for VR games seemed to go through an exploratory process, which was not observed among non-VR games in the same period. The results offer insights into how the focus of RNPs’ marketing evolves as their newness fades.

From Rivers to Confetti: Reconfigurations of Time through New Media Narratives

From Rivers to Confetti: Reconfigurations of Time through New Media Narratives

Deep Refinement: capsule network with attention mechanism-based system for text classification

Most of the text in the questions of community question–answering systems does not consist of a definite mechanism for the restriction of inappropriate and insincere content. A given piece of text can be insincere if it asserts false claims or assumes something which is debatable or has a non-neutral or exaggerated tone about an individual or a group. In this paper, we propose a pipeline called Deep Refinement which utilizes some of the state-of-the-art methods for information retrieval from highly sparse data such as capsule network and attention mechanism. We have applied the Deep Refinement pipeline to classify the text primarily into two categories, namely sincere and insincere. Our novel approach ‘Deep Refinement’ provides a system for the classification of such questions in order to ensure enhanced monitoring and information quality. The database used to understand the real concept of what actually makes up sincere and insincere includes quora insincere question dataset. Our proposed question classification method outperformed previously used text classification methods, as evident from the F1 score of 0.978.

Looking into the Operational Modalities Adopted in Some of the POS Tagging Tools in Identification of Contextual Part-of-Speech of Words in Texts

Part-of-speech (POS) tagging is an indispensable method of text processing. The main aim is to assign part-of-speech to words after considering their actual contextual syntactic-cum-semantic roles in a piece of text where they occur (Siemund & Claridge 1997). This is a useful strategy in language processing, language technology, machine learning, machine translation, and computational linguistics as it generates a kind of output that enables a system to work with natural language texts with greater accuracy and success. Part-of-speech tagging is also known as ‘grammatical annotation’ and ‘word category disambiguation’ in some area of linguistics where analysis of form and function of words are important avenues for better comprehension and application of texts. Since the primary task of POS tagging involves a process of assigning a tag to each word, manually or automatically, in a piece of natural language text, it has to pay adequate attention to the contexts where words are used. This is a tough challenge for a system as it normally fails to know how word carries specific linguistic information in a text and what kind of larger syntactic frames it requires for its operation. The present paper takes up this issue into consideration and tries to critically explore how some of the well-known POS tagging systems are capable of handling this kind of challenge and if these POS tagging systems are at all successful in assigning appropriate POS tags to words without accessing information from extratextual domains. The novelty of the paper lies in its attempt for looking into some of the POS tagging schemes proposed so far to see if the systems are actually successful in dealing with the complexities involved in tagging words in texts. It also checks if the performance of these systems is better than manual POS tagging and verifies if information and insights gathered from such enterprises are at all useful for enhancing our understanding about identity and function of words used in texts. All these are addressed in this paper with reference to some of the POS taggers available to us. Moreover, the paper tries to see how a POS tagged text is useful in various applications thereby creating a sense of awareness about multifunctionality of tagged texts among language users.

Quantum Structure in Cognition: Human Language as a Boson Gas of Entangled Words

We model a piece of text of human language telling a story by means of the quantum structure describing a Bose gas in a state close to a Bose–Einstein condensate near absolute zero temperature. For this we introduce energy levels for the words (concepts) used in the story and we also introduce the new notion of ‘cogniton’ as the quantum of human thought. Words (concepts) are then cognitons in different energy states as it is the case for photons in different energy states, or states of different radiative frequency, when the considered boson gas is that of the quanta of the electromagnetic field. We show that Bose–Einstein statistics delivers a very good model for these pieces of texts telling stories, both for short stories and for long stories of the size of novels. We analyze an unexpected connection with Zipf’s law in human language, the Zipf ranking relating to the energy levels of the words, and the Bose–Einstein graph coinciding with the Zipf graph. We investigate the issue of ‘identity and indistinguishability’ from this new perspective and conjecture that the way one can easily understand how two of ‘the same concepts’ are ‘absolutely identical and indistinguishable’ in human language is also the way in which quantum particles are absolutely identical and indistinguishable in physical reality, providing in this way new evidence for our conceptuality interpretation of quantum theory.

The Public Sentiment and Emotional Variations in Social Media using Twitter Dataset

The collection of applications (internet followed) that provide way to create communication of user-generated matter by the social media (Twitter, Facebook, Whatsapp, etc.,). Twitter is the micro-blogging platform. Thoughts and opinions about different aspects are shared by users. Analysis on sentiment expressed in a piece of text which expresses opinions, towards a particular topic, product, etc. (positive, negative, or neutral). Primary issues are previous techniques that have biased classification accuracy, due to data distribution in a non-balanced way. The existing methods are applied over small dataset which cannot be extended for generalization with expected accuracy. "Curse of dimensionality” still exists with higher number of attributes in existing methods. Weaker classification in non-linear context. Limited use of transforms (kernels) for linearity in higher dimensional spaces and lack of parameter tuning. In most of the real time dataset the neutral class is very high. The proposed system is the framework for text mining to handle theme extraction from twitter opinion dataset. The Learning models to be built using the Support Vector Tool (SVT) classification method with a kernel trick applied with composition using unigram, bigram and hybrid (unigram + bigram) features. The performance to be obtained by tuning the internal parameters. The result shows that SVT linear kernel with hybrid features are the best classifier when compare to other classifiers with maximum accuracy from the twitter opinion dataset.

An Automated Tool for Detection and Tutoring of Sources of Ambiguities in Requirements Documents

Software Engineering (SE) is the application of essentials to deal with the analysis, design, development, testing, deployment and management - Software Development Life Cycle (SDLC) - of software systems. Requirements Engineering (RE) is responsible for the most critical task in the SDLC; which is transforming the requirements and wishes of the software users into complete, accurate and formal specifications. One of the main responsibilities of RE is the creation of a software requirements document that exactly, reliably, and totally defines the functional and non-functional properties of the system to be developed. At some point through the RE process, the requirements are written using a Natural Language (NL). On one hand, NLs are flexible, common, and popular. On the other hand, NLs are recognized widely as inherently ambiguous. Ambiguity is noticed in a requirement document when a piece of text is interpreted in distinct ways. This may lead to erroneous software that is too expensive to correct in later phases of the SDLC. Many tools have been developed in the literature to detect ambiguities in requirements documents. Best practices for writing requirements have also been proposed to help avoid ambiguities in the first place. The goal of this paper is to combine features from both approaches by developing the Ambiguity Checker Tutor (ACTutor), which not only detects ambiguities, but also aids in tutoring requirements engineers to apply best practices while writing requirements (rather than merely listing them). The paper is mainly concerned with proving the tutoring effectiveness of ACTutor through empirical evaluation.

An Enhanced Technique for Analyzing Sentiments of Public Reviews - I

Sentiment analysis is the process of extracting the opinion expressed in a piece of text to determine the writer’s attitude towards a topic, product or any service in general and classify it into classes such as positive, negative or neutral. Bag of Words is the traditional approach for text representation in Sentiment Analysis where text is represented as bag of its words. This approach represents the text by breaking the sentence into words disregarding other semantic information. A problem that occurs due to this representation is Polarity Shift problem. To address polarity shift problem a dual sentiment analysis (DSA) system is created. It looks at the reviews from both the sides i.e. positive and negative. The existing work on dual sentiment analysis includes techniques where dual training and dual prediction is performed. The proposed system is to enhance the classification performance of the existing system by applying different classifiers apart from those used in existing system to obtain better results. After classification of reviews into appropriate classes, various graphs are plotted based on different parameters to validate the results and determine the best classifier from the applied classifiers.

Finding decision jumps in text classification

Text classification is one of the key problems in natural language processing (NLP), and in early years, it was usually accomplished by feature-based machine learning models. Recently, the deep neural network has become a powerful learning machine, making it possible to work with text itself as raw input for the classification problems. However, existing neural networks are typically end-to-end and lack explicit interpretation of the prediction. In this paper, we propose Jumper, a novel framework that models text classification as a sequential decision process. Generally, Jumper is a neural system that scans a piece of text sequentially and makes classification decisions at the time it wishes, which is inspired by the cognitive process of human text reading. In our framework, both the classification result and when to make the classification are part of the decision process, controlled by a policy network and trained with reinforcement learning. Experimental results of real-world applications demonstrate the following properties of a properly trained Jumper: (1) it tends to make decisions whenever the evidence is enough, therefore reducing total text reading by 30–40% and often finding the key rationale of the prediction; and (2) it achieves classification accuracy better than or comparable to state-of-the-art models in several benchmark and industrial datasets. We further conduct a simulation experiment with mock data, which confirms that Jumper is able to make a decision at the theoretically optimal decision position.

Analyzing the Sentiment of MOOC Discussion Posts

The purpose of the project is to identify common difficulties that learners may face and to understand their emotions as they progress through MOOCs. MOOC is an abbreviation for the Massive Open Online Course and the research deals with the data from ten different courses from Coursera. The data is used to extract pieces of text that students have made. Then, those certain texts are required to be sent to Google Cloud Natural Language API. This app allows users to get a sentiment analysis of a text. The main goal is to assist instructors with monitoring MOOC to make it more efficient and easier for students to progress since it assists to improve the courses.
 To achieve this, the first step is to gather all the data from each of the courses. Then use programming to dump all that data into one big database. The program that is used here is called Pycharm and user is required to use python and sql to aid him in dumping the data in the database. Once the database is created, coding is done to only select out the pieces of information that are needed. These texts should be where students make comments or ask questions. Next, the data is queried to send these texts to Google Cloud Natural Language API. Here, the program breaks down all the sentences to only be just words. Then the program is going to categorize each word according to whether its connotation is positive, negative or neutral. Next, all the words are sorted according to their connotations. The overall sentiment depends on the emotion that has the highest number. If positives and negatives are all balanced out then the sentiment is neutral. Sentiment scores range from -1 to 1, where -1 is the most negative, 1 is the most positive and anywhere near 0 is neutral.
 Positive sentiment scores indicate instructors that students are doing well on their course and neutral sentiment scores indicate that the course is balanced out with difficulties and easy tasks. However, negative sentiment is the most important to instructors since it indicates them that students are struggling and they need to improve the course.