Piece Of Text Research Articles

Question Entailment on Developing Indonesian Covid-19 Question Answering System

Despite the severe impact of COVID-19 on humans has already decreased, people still need to be aware of the recent disease information. A continually updated Frequently Asked Questions (FAQ) system could help the public get valid and relevant information. To maintain a FAQ system manually needs much effort, hence an approach to develop the system automatically is needed. Question Answering System (QAS) is a system that can accept input in question sentences and produces an answer quickly, concisely, and relevantly, and could be used to provide COVID-19 information to the public. One method on developing a QAS is Recognizing Question Entailment (RQE). RQE is a form of relationship based on a cause-and-effect relationship between two pieces of text called text (T) and hypothesis (H). We present a study on developing Covid-19 QAS in Bahasa Indonesia using RQE. The datasets are collected from reputable sources and consist of 725 pairs of questions and answers. The experimental results show that the best performance results were obtained using the Logistic Regression model in training set 1, which contains 54.2% of positive question pairs and 45.8% of negative question pairs with an f-measure value of 83.65%. These results indicate that the RQE method can identify the entailment between new questions and questions in the dataset well.

Beyond word embeddings: A survey

The goal of this paper is to provide an overview of the methods that allow text representations with a focus on embeddings for text of different lengths, specifically on works that go beyond word embeddings. Analyzing pieces of text can be more challenging in comparison to the analysis of single words, because several additional factors come into play. For this reason, representations of longer pieces of text can be obtained with different strategies, leveraging additional information with respect to what is done for single words. A text is defined by its components and how these are combined together, and this should be taken into account when integrating information to obtain a single document embedding. In addition, multimodal approaches are described to show how it is possible to fuse information of different nature (aural, visual and knowledge) in order to obtain enriched representations. The aim of this survey is to help navigate through the existing methods proposed in the literature and understand which strategies are most suitable to specific needs.

Anatomy of Sentiment Analysis of Tweets Using Machine Learning Approach

Sentiment Analysis (SA) is an efficient way of determining people’s opinions from a piece of text. SA using different social media sites such as Twitter has achieved tremendous results. Twitter is an online social media platform that contains a massive amount of data. The platform is known as an information channel corresponding to different sites and categories. Tweets are most often publicly accessible with very few limitations and security options available. Twitter also has powerful tools to enhance the utility of Twitter and a powerful search system to make publicly accessible the recently posted tweets by keyword. As popular social media, Twitter has the potential for interconnectivity of information, reviews, updates, and all of which are important to engage the targeted population. In this work, numerous methods that perform a classification of tweet sentiment on Twitter have been discussed. There has been an extensive research studies in the field of SA of Twitter data. This study provides a comprehensive analysis of the most standard and widely applicable opinion mining techniques based on machine learning and lexicon-based along with their metrics. The proposed work is helpful in informaiton analysis in the tweets where opinions are found heterogeneous, unstructured, polarised negative, positive, or neutral. In order to validate the supremacy of the suggested approach, we have executed a series of experiments on the real-world Twitter dataset that alters to show the effectiveness of the proposed framework. This research effort also highlighted the recent challenges in the SA field and the proposed work’s future scope.

Review: Intimate Alien: The Hidden Story of the UFO, by David J. Halperin

Review: <i>Intimate Alien: The Hidden Story of the UFO</i>, by David J. Halperin

Barriers and Opportunities for Physical Activities: A Way Forward for Pregnant Individual

A woman's physical activity may change during pregnancy, a life-changing event. Working individuals, middle-aged adults, pregnant women, and seniors all have greater health and wellbeing when they participate in leisure activities. Improvements in physiological, metabolic, and psychological factors as well as a lower risk of illness and death are linked. According to current recommendations, both pregnant and non pregnant people should exercise moderately every day for at least 30 minutes. To pave the way for appropriate and sufficient physical activities that best suit pregnant women's conditions, the goal of this review was to examine the adequate physical activities for pregnant women, pregnant women's exercise ideas, barriers to physical activity, suggestions for overcoming physical activity barriers, and benefits associated with physical activities for pregnant women. The most current studies on the barriers pregnant women face while engaging in physical activity and the associated advantages they can provide will be discussed. Data was taken from a variety of literature reviews that have been published in peer-reviewed journal articles, but only English-language studies that had been published between 2015 and 2022 were taken into consideration for this study. For information, researchers used the databases of Google Scholar, Microsoft Academic, ProQuest, PLoS One, Cochrane Library, JSTOR, Microsoft Academic, and Pubmed. Although there were several papers on the issue, only a small number of text pieces were included for this review. According to the reviewed articles, the studies pointed to the fact that exercise and recreation in the second and third trimesters lower the risk of caesarean birth. Thus, improved strategies to engage pregnant women in physical activities would be welcome.

DISCOVERING THE IMPLIED MEANING OF SIGNS USED IN TOOTHPASTE ADVERTISEMENT VIDEOS

Companies use advertisements to promote their products and send particular messages for the target audiences. An advertisement is a piece of text that tells people about something which includes persuading people to buy a product or service. In general, an advertisement is used to introduce a product by a certain company since it has the power to influence and persuade people to do particular action. Signs are commonly used in advertisements so that it is attractive and can convey messages efffectively. This study aimed to analyze the meaning of verbal and non-verbal signs which found in Colgate toothpaste advertisement videos. This study used Colgate toothpaste advertisement videos which taken from YouTube. The theories used in this study are the semiotic theory by Saussure (1983) to determine verbal and non-verbal signs and the theory of meaning by Barthes (1977) to discover the implied meaning of verbal and non-verbal signs found in Colgate toothpaste advertisements. This study uses the descriptive method to analyze the data. As the result, the advertisements show the verbal and visual signs support the company in promoting and informing its product. In this study, connotative meaning occurred dominantly rather that denotative meaning because the advertisements used more hidden meanings rather than literal meaning to convey the messages toward the audiences.

A reinforced active learning approach for optimal sampling in aspect term extraction for sentiment analysis

Aspect level sentiment analysis is a fine grained task in sentiment analysis which identifies the product features from an opinionated piece of text and maps the sentiment towards each of them. Supervised ML algorithms have reported comparatively higher performance on aspect level sentiment analysis but at the cost of substantial qualitative labelled data. Data labelling for such fine grained tasks also demand domain knowledge and expertise. Hence a mechanism to extract a minimal informative subset which is almost representative of the entire data would be a breakthrough in bringing down the annotation costs to a large extent. The proposed methodology puts forward an active learning based sampling strategy for aspect term extraction, a subtask in aspect level sentiment analysis which identifies the product features. The sampling strategy is automated by reinforcement learning which extracts an optimal sample from the entire unlabelled training data and hence optimizes data annotation by reducing the time and effort linked to the labelling process. This work is of high importance in a data driven era where companies invest a lot in collecting and annotating huge volumes of data. The model has been experimented across the laptop and restaurant domains of SemEval (2014–2016) datasets. The experiments proved that a considerable reduction of the training data size is achieved across different datasets. The model trained on the data extracted by the proposed reinforced active learning model beats random sampling by 9 to 17 points when evaluated on the F-measure of the extracted aspect terms and is almost on par with the model trained on the entire training data by utilising hardly 9 to 13% of the entire training data across the datasets experimented.

Aspect2Labels: A novelistic decision support system for higher educational institutions by using multi-layer topic modelling approach

Aspect-based sentiment analysis (ABSA) has gained a rising concentration recently. It aims to provide a set of aspect terms and sentiments from a piece of text. Educational Data Mining (EDM) is now an essential tool for analysing pedagogical data. In academic institutions, student feedback is an influential gauge to measure the quality of the teaching–learning process. It helps higher education institutions to reconsider and improve their policies for student recruitment and retention. This paper proposed a situation awareness multi-layer topic modelling and enhanced hybrid machine learning approach for evaluating students’ textual feedback data in academic institutions. The proposed Aspect2Labels (A2L) approach is divided our system into three layers. To preserve semantic information, we extracted general aspects terms in the first layer known as high-level aspects. We pulled low-level aspects terms associated with high-level aspect terms in the second layer and the third layer used for sentiment orientation. We used zero-shot learning, LDA, and different variants of LDA for the aspect extraction process. We performed annotation on unlabelled students’ comments using our proposed A2L approach, and we obtained 91.3% accuracy in this process. We developed and tested novel algorithms for aspect terms mapping to label each aspect term to corresponding feedback. Different machine learning algorithms have been used to classify sentiments according to extracted aspects. We have also proposed and used Variable Global Feature Selection Scheme (VGFSS) and Variable Stopwords Filtering (VSF) to improve the performance of classifiers. We have managed to get 97% and 93% accuracy on the test dataset using Support Vector Machine (SVM) and Artificial Neural Networks (ANN), respectively. We highly suggest that our novel approach of aspect-oriented sentiment analysis could provide adequate understanding to analyse students’ feedback.

Latent graph learning with dual-channel attention for relation extraction

As a building block of information retrieval, relation extraction aims at predicting the relation type between two given entities in a piece of text. This task becomes challenging when it is confronted with long text that contains many task-unrelated tokens. Recent attempts to solve this problem have resorted to learning the relatedness among tokens. However, how to obtain appropriate graph for better relatedness representation still remains outstanding, while existing methods have room to improve. In this paper, we propose a novel latent graph learning method to enhance the expressivity of contextual information for the entities of interest. In particular, we design a dual-channel attention mechanism for multi-view graph learning and pool the learned multi-views to sift unrelated tokens for latent graph. This process can be repeated many times for refining the latent structure. We show that our method achieves superior performance on several benchmark datasets, compared to strong baseline models and prior multi-view graph learning approach.

Exploring Finnic written oral folk poetry through string similarity

Abstract Suomen Kansan Vanhat Runot (Old Poems of the Finnish People) is a collection of nearly 90,000 oral folk poems written down between 1564 and the early 20th century. It is characterized by frequent reoccurrence of similar pieces of text on various levels (from entire poems, through passages to single verses and collocations). However, finding these similarities is challenging due to a high degree of orthographical, morphological, and compositional variation. In this article, we propose a method for automatically identifying equivalent verses, i.e. verses conveying the same meaning with the same words, using a clustering based on cosine similarity of character bigram vectors. The method achieves around 81% F-score and has been successfully used for identifying similarities across the entire SKVR corpus on the level of verse, passage, and poem. The results can be browsed through a Web interface.

Analysis Based on Social Media using Multi Modal Algorithm

Propose system tend to concentrate on analysis sentiment of text from social media, aim of system is to find whether piece of text is positive or negative. The goal of Sentiment Analysis is to harness this data in order to obtain important information regarding public opinion that would help make smarter business decisions, political campaigns and better product consumption. Sentiment Analysis focuses on identifying whether a given piece of text is subjective or objective and if it is subjective, then whether it is negative or positive. Sentiment analysis deals with the computational treatment of opinion, sentiment, and subjectivity of texts. Moreover, we tend to conjointly develop economical illation methodology for parameter estimation of sup- ported folded Gibbs sampling. We tend to judge SJASM extensively on real-world review knowledge, and experimental results demonstrate that the planned model outperforms seven well-established base- line strategies for sentiment analysis tasks.

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training

The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a local news outlet, a social media platform, a news forum, etc. Most research on stance detection, however, has been limited to working with a single language and on a few limited targets, with little work on cross-lingual stance detection. Moreover, non-English sources of labelled data are often scarce and present additional challenges. Recently, large multilingual language models have substantially improved the performance on many non-English tasks, especially such with a limited number of examples. This highlights the importance of model pre-training and its ability to learn from few examples. In this paper, we present the most comprehensive study of cross-lingual stance detection to date: we experiment with 15 diverse datasets in 12 languages from 6 language families, and with 6 low-resource evaluation settings each. For our experiments, we build on pattern-exploiting training (PET), proposing the addition of a novel label encoder to simplify the verbalisation procedure. We further propose sentiment-based generation of stance data for pre-training, which shows sizeable improvement of more than 6% F1 absolute in few-shot learning settings compared to several strong baselines.

Tracing Origin of Social Media Posts

This problem statement should result in a solution that can identify perpetrators who first posted sexually explicit abuse content on social media platforms. Images and videos of individuals of a sexually explicit nature are quite often posted online intentionally by perpetrators on various social media platforms with the sole intent of causing harassment, humiliation and distress to the victim. Social media platforms are constantly trying to create and improve automatic mechanisms to identify and reject such content at the time of upload itself. However, there are times when such content containing nudity and of a sexually explicit nature, fails to be detected at the time of upload and gets published. Such content usually has a tendency to instantly become viral, and others thereafter share it, or download and post and it again from their social media accounts. Social media platforms take down such posts when reported but by the time this is done, several copies have already been made and go in circulation. It quickly becomes ambiguous as to who posted it first, and taking advantage of this ambiguity, the original perpetrator evades detection. It is therefore critical to identify the person who first posted such distressing content online. Given a piece of text, image or video snippet as input, build a solution that can identify the person who was the first one to post it online on a particular social media platform. Please bear in mind that people could have copied it and made minor modifications before re-posting it from their accounts. Participants are expected to obtain suitable data required to work on this problem statement on their own.

SETTING THE STAGE FOR THE SUN: Interrogations of performance of flicker

Flicker is a coordinated beat which can be superimposed on the brain’s alpha rhythm, through a flickering light source, and is associated with hallucinatory or visionary states of mind. In this experimental piece, I weave ideas and performance into a poetic image and text piece proposing some hypotheses and questions surrounding the relationship of moving bodies, the sun, and eureka moments of visions and dreams of new worlds.

INTRODUCTION

INTRODUCTION

Chemical-Protein Relation Extraction with Pre-trained Prompt Tuning.

Biomedical relation extraction plays a critical role in the construction of high-quality knowledge graphs and databases, which can further support many downstream applications. Pre-trained prompt tuning, as a new paradigm, has shown great potential in many natural language processing (NLP) tasks. Through inserting a piece of text into the original input, prompt converts NLP tasks into masked language problems, which could be better addressed by pre-trained language models (PLMs). In this study, we applied pre-trained prompt tuning to chemical-protein relation extraction using the BioCreative VI CHEMPROT dataset. The experiment results showed that the pre-trained prompt tuning outperformed the baseline approach in chemical-protein interaction classification. We conclude that the prompt tuning can improve the efficiency of the PLMs on chemical-protein relation extraction tasks.

Use of sentiment analysis in social media campaign design and analysis

Sentiment Analysis is the process by which opinions are defined and categorized as positive, neutral, or negative in a given piece of text. It is a vital part of every strategy for tracking social media. It helps to understand what someone is thinking behind a social media post. Knowing the emotion will provide valuable background for the businesses to move further and react. Over the last decade, numerous studies have been carried out on how businesses can use Sentiment Analysis to understand and quantify the feelings of their consumers about their brand, products, and services. An in-depth analysis of the existing empirical literature on SA regarding social media campaigns is provided using a systematic review of the literature. This paper presents the findings according to the preferred reporting items for systematic reviews and meta-analysis (PRISMA). The aim is to create a resource of the methods and techniques used in the studies to assist both researchers and academia. We subsequently identified the corpus trends, challenges, and implications. We suggested avenues for further research in the application of SA in social media campaign design and analysis.

Using Student Feedback to Analyze the Characteristics of Presence in Classroom Settings Based on the Community of Inquiry Framework

The community-of-inquiry (CoI) framework on presence points out the direction for the effective teaching of teachers. Feedback plays an important role during the teaching process in the promotion of teaching and learning. A total of 476 pieces of feedback text, including 1695 short sentences, were collected from 13 classes of a Modern Educational Technology course, and then they were coded and analyzed on the basis of the cognitive, teaching, social, and emotional dimensions. It was found that the CoI theory is also suitable for classroom settings, and in situations where all of the presences exist. Among them, emotional presence is the most common, followed by the cognitive and teaching presences, while social presence is the least common. The result may help teachers to optimize course design and implementation for enhancing presence, improving learning experiences, and promoting high-quality learning. Moreover, the research results provide references for studying data-based precision teaching.

Text Summarization using Extractive and Abstractive Techniques

There have been considerable advancements in Text Summarization over the last few years. There are two ways to text summarization: one is based on natural language processing (NLP), and the other is based on deep learning. In the realm of NLP, text summarization is the most intriguing and challenging task. NLP stands for Natural Language Processing, which studies and manipulates human language by computers. Because of the massive increase in information and data, it has become critical. Text summarization is creating a thorough and meaningful summary of text from various sources such as books, news stories, research papers, and tweets, among others. Large text documents that are difficult to summarize manually are the research subject. The job of condensing a piece of text into a shorter version, minimizing the size of the original text while maintaining key informative components and content meaning, is known as summarising. Because human text summarising is a time-consuming and intrinsically tiresome process, automating it is gaining popularity and hence acts as a potent stimulus for academic study.

Towards Sustainable Living through Sentiment Analysis during Covid19

Artificial intelligence is the process of the machine to perform with the simulation of human intelligence. Computing within the field of emotions paves the recognitions to sentiment analysis. Sentiment analysis is the method of capturing the emotions behind a text whether or not it's positive, negative or neutral. Sentiment Analysis (SA) or Opinion Mining (OA) is the process to provide computational treatment to unstructured data to categorize and identify the sentiments or emotions expressed in a piece of text. It combines Natural Language Processing Techniques and Machine Learning Techniques. This technology is additionally referred to as opinion mining or feeling computing. Sentiment Analysis uses the ideas of machine learning alongside an AI based process called NLP to extract and analyze the data, emotions, information from the text. This work explores the impact of social media during covid 19 and possible link between sustainable living and health care with the usage of sentiments. This paper address the sustainable development goal 3 (good health and wellbeing) of SDG 2030 and a possible way towards sustainable living through sentiment analysis.