Short Text Analysis Research Articles

A combined AraBERT and Voting Ensemble classifier model for Arabic sentiment analysis

For sentiment analysis of short texts (e.g. movie reviews, tweets, etc.), one approach is to build machine learning models that can determine their tones (positive, negative, neutral). However, these natural language processing (NLP) studies are missing when there is a lack of high-quality and large-scale training data for specific languages such as Arabic. In this paper, we present three machine learning models designed to classify sentiment Arabic tweets developed for a Kaggle competition. We present a Voting Ensemble classifier taking advantage of both character-level and word-level features. We also propose an AraBERT (Arabic Bidirectional Encoder Representations from Transformers) model with preprocessing using Farasa Segmenter. Finally, we combine these first two approaches as a third approach (Voting Ensemble classifier using AraBERT embeddings). Performance measures of results show improvement over previous efforts for all models. The third model exhibits strong performance with a 73.98% F-score score. The work presented here could be useful for future studies and for new Arabic sentiment analysis online services or competitions.

Sentiment Analysis of Short Texts Using SVMs and VSMs-Based Multiclass Semantic Classification

ABSTRACT In our approach, a hybrid machine learning model is proposed which uses Enhanced Vector Space Model (EVSM) along with Hybrid Support Vector Machine (HSVM) classifier. Initially the social media-based information is retrieved using Enhanced Vector Space Model (EVSM). EVSMs are employed in order to characterize the text content by mapping them into high-dimensional vector spaces, capturing the relationships between words and their contextual meanings. Rigorous feature selection methods are employed to designate texts for review, and a multiclass semantic classification algorithm, specifically the HSVM classifier, is utilized for categorization. Decision tree algorithm is used along with SVM to refine the selection process. To enhance sentiment analysis accuracy, sentiment dictionaries are not only presented but also extended through the expansion of Stanford’s GloVE tool. To enhance precision, the proposed work introduces weight-enhancing methods for processing renowned text weights. Sentiments are classified into positive, negative, and neutral categories. Notably, the achieved results demonstrate improved accuracy, attributed to the incorporation of an emotional sentiment enhancement factor for determining weights and leveraging sentiment dictionaries for word availability. The accuracy is obtained to be 92.78% with 91.33% positive sentiment rate and 97.32% negative sentiment rate.

Flash fiction as a distinct literary form: some thoughts on time, space, and context

ABSTRACT This article combines a craft-focused approach with a stylistics perspective to consider the ways in which flash fiction may be said to operate as a unique literary form. In the opening section flash fiction is defined in relation to what are usually seen as its two closest literary companions: prose poetry and the short story. This is followed by an introduction to the linguistic phenomenon known as deixis, and to related concepts from the field of Narratology. These ideas are subsequently illustrated and explored through the close analysis of several short texts and used to uncover what might be considered the defining features of the form. The earlier taxonomic approach of William Nelles is also evaluated in the light of more recent creative practice. The article concludes by arguing that the mobilisation of a story world is a necessary requirement for a text to be classified as flash fiction, by highlighting the importance of deft manipulation of deictic elements, and finally by suggesting that the unique communicative context evoked by flash fiction has significant implications for its interpretation.

Penderitaan Tokoh Minut dalam Cerpen Ibu Tiri Karya Afifah Ardi

This journal writing is based on the short story stepmother by Afifah Ardi. Explains and provides an in-depth picture of what the character Minut faces, a child who experiences physical violence from his stepmother and bears the burden of being a substitute mother for his younger siblings. The formulation of the problem is how the physical violence and mental pressure experienced by the character Minut can affect his physical and psychological development. The background of this short story is related to the phenomenon of family violence and its long-term impact on children. The research method used is hermeneutics, with a focus on interpretation and analysis of short story texts. The theoretical study includes previous research on violence against female characters in literature and its relevance to the suffering of Minut characters. The results of the discussion show that physical violence and mental pressure have an impact not only physically, but also psychologically, creating an internal struggle for Minut’s character between obligation and personal bitterness. Minut’s character, even though he is full of disappointment, resentment and fatigue, still shows strength of character in protecting his younger siblings. The conclusion highlights the urgency of raising awareness of family violence and the need for action to protect children’s rights.

РЕЦЕНЗИЯ НА УЧЕБНОЕ ПОСОБИЕ Т. Д. БЕЛОВОЙ «ГОРЬКИЙ. «РАССКАЗЫ 1922-1924 ГОДОВ»: МОТИВЫ, ОБРАЗЫ СМЫСЛЫ. ПРОБЛЕМЫ СОВРЕМЕННОГО ПРОЧТЕНИЯ»

The review is devoted to the textbook by T. D. Belova, which analyzes the publication of M. Gorky “Stories of 1922-1924”. The researcher builds the reading and analysis of short Gorky texts on the involvement of various contexts: biographical, creative, socio-cultural. At the same time, both the collection of stories and each individual text are considered with the assistance of scientific and critical works from different times. The author of the manual offers a new look at Gorky’s publication, prepared and published abroad, but it concerns Russia contemporary to Gorky, and he seeks to comprehend both the past of his home country and its present.

Revisiting Probabilistic Relation Analysis: Using Probabilistic Relation Graphs for Relational Similarity Analysis of Words in Short Texts

Relation graphs provide useful tools for structural and relational analyses of highly complex multi-component systems. Probabilistic relation graph models can represent relations between system components by their probabilistic links. These graph types have been widely used for the graphical representation of Markov models and bigram probabilities. This study presents an implication of relational similarities within probabilistic graph models of textual entries. The article discusses several utilization examples of two fundamental similarity measures in the probabilistic analysis of short texts. To this end, the construction of probabilistic graph models by using bigram probability matrices of textual entries is illustrated, and vector spaces of input word-vectors and output word-vectors are formed. In this vector space, the utilization of cosine similarity and mean squared error measures are demonstrated to evaluate the probabilistic relational similarity between lexeme pairs in short texts. By using probabilistic relation graphs of the short texts, relational interchangeability analyses of lexeme pairs are conducted, and confidence index parameters are defined to express the reliability of these analyses. Potential applications of these graphs in language processing and linguistics are discussed on the basis of the analysis results of example texts. The performance of the applied similarity measures is evaluated in comparison to the similarity index of the word2vec language model. Results of the comparative study in one of the illustrative examples reveal that synonyms with 0.18157 word2vec similarity value scored 1.0 cosine similarity value according to the proposed method.

Improving students’ punctuation: classroom experimentation and results in texts by primary and secondary school students in Quebec

The texts of primary and secondary school students show a high proportion of written errors related to punctuation (Boivin and Pinsonneault, 2018, among others). Yet punctuation instruction often offers students only limited opportunities to improve their control of sign usage in a writing context (Riverin and Dufour, 2018). This article presents a quasi-experimental study involving 16 French classes from cycle 3 of primary school and cycle 1 of secondary school in Quebec (age 10 to 13). Students in the experimental groups carried out a sequence of 20 activities implementing three innovative didactic devices, designed during a first phase of the research, in collaboration with the participating teachers. The aim was to improve punctuation and syntax in writing. We will present results drawn from the analysis of short texts written at pre-test and post-test (two texts at each time: one descriptive and one narrative) in the experimental and control groups, in relation to success variables in segmentation into graphic sentences (capital letter & full stop), and in punctuation within graphic sentences and syntactic sentences (clauses, i.e. subject + predicate (+ sentence adverbial(s)), for some comma usage rules.

Short text classification with machine learning in the social sciences: The case of climate change on Twitter.

To analyse large numbers of texts, social science researchers are increasingly confronting the challenge of text classification. When manual labeling is not possible and researchers have to find automatized ways to classify texts, computer science provides a useful toolbox of machine-learning methods whose performance remains understudied in the social sciences. In this article, we compare the performance of the most widely used text classifiers by applying them to a typical research scenario in social science research: a relatively small labeled dataset with infrequent occurrence of categories of interest, which is a part of a large unlabeled dataset. As an example case, we look at Twitter communication regarding climate change, a topic of increasing scholarly interest in interdisciplinary social science research. Using a novel dataset including 5,750 tweets from various international organizations regarding the highly ambiguous concept of climate change, we evaluate the performance of methods in automatically classifying tweets based on whether they are about climate change or not. In this context, we highlight two main findings. First, supervised machine-learning methods perform better than state-of-the-art lexicons, in particular as class balance increases. Second, traditional machine-learning methods, such as logistic regression and random forest, perform similarly to sophisticated deep-learning methods, whilst requiring much less training time and computational resources. The results have important implications for the analysis of short texts in social science research.

A Hybrid Spam Detection Framework for Social Networks

The widespread use of social networks has caused these platforms to become the target of malicious people. Although social networks have their own spam detection systems, these systems sometimes may not prevent spams in their social networks. Spam contents and messages threaten the security and performance of users of these networks. A spam account detection framework based on three components is proposed in this study. Short link analysis, machine learning and text analysis are the components used together in the proposed framework. First, a dataset was created for this purpose and the attributes of spam accounts were determined. Later, the hyperlinks in the messages in this dataset were analyzed through link analysis component. The machine learning component was modelled through attributes. Moreover, the messages of the social network users were analyzed through text analysis method. A web-based application of the proposed model was put into practice. As a result of the experimental studies carried out thanks to the framework, it was determined that the proposed framework showed a performance of 95.69 %. The success of this article was calculated according to the F-measure and precision evaluation metrics under the influence of sensitive content rate. It is aimed to detect spam accounts on social network and the spam detection policy of these networks is intended to support.

Incorporating structural topic modeling into short text analysis

Abstract The past few decades have seen the rapid development of topic modeling. So far, research has been more concerned with determining the ideal number of topics or meaningful topic clustering words than with applying topic modeling techniques to evaluate linguistic theories. This study proposes the Structural Topic Model (STM)-led framework to facilitate the interpretation of topic modeling results and standardize text analysis. STM encompasses various model training mechanisms, thereby requiring systematic designs to properly combine language studies. “Structural” in STM refers to the inclusion of metadata structure. Unlike the corpus-based keyness approach, STM can capture contextual cues and meta-information for the interpretation of topical results. Besides, STM can make cross-corpora comparisons via topical contrast, a challenging task for corpus-driven related models such as the Biterm Topic Model (BTM). Stylistic variations in song lyrics are taken as an illustration to show how to use the suggested framework to delve into the linguistic theory proposed by Pennebaker (2013). The topical model and iterable model in the proposed paradigm can clarify how pronouns affect style distinction. We believe the proposed STM-led framework can shed light on text analysis by conducting a reproducible cross-corpora comparison on short texts.

Lasso-based variable selection methods in text regression: the case of short texts

Communication through websites is often characterised by short texts, made of few words, such as image captions or tweets. This paper explores the class of supervised learning methods for the analysis of short texts, as an alternative to unsupervised methods, widely employed to infer topics from structured texts. The aim is to assess the effectiveness of text data in social sciences, when they are used as explanatory variables in regression models. To this purpose, we compare different variable selection procedures when text regression models are fitted to real, short, text data. We discuss the results obtained by several variants of lasso, screening-based methods and randomisation-based models, such as sure independence screening and stability selection, in terms of number and importance of selected variables, assessed through goodness-of-fit measures, inclusion frequency and model class reliance. Latent Dirichlet allocation results are also considered as a term of comparison. Our perspective is primarily empirical and our starting point is the analysis of two real case studies, though bootstrap replications of each dataset are considered. The first case study aims at explaining price variations based on the information contained in the description of items on sale on e-commerce platforms. The second regards open questions in surveys on satisfaction ratings. The case studies are different in nature and representative of different kinds of short texts, as, in one case, a concise descriptive text is considered, whereas, in the other case, the text expresses an opinion.

An Ensemble Multi-Layered Sentiment Analysis Model (EMLSA) for Classifying the Complex Datasets

Sentiment analysis is one domain that analyzes the feelings and emotions of the users based on their text messages. Sentiment analysis of short messages, reviews in online social media (OSM), and social networking sites (SNS) messages gives the analysis of given text data. Processing short text and SNS messages is a very tedious task because of the restricted detailed information generally contained. Solving this issue requires advanced techniques that are combined to give accurate results. This paper developed an Ensemble Multi-Layered Sentiment Analysis Model (EMLSA) that exploits the trust-based sentiment analysis on various real-time datasets. EMLA is the combined approach with VADER (Valence Aware Dictionary and sEntiment Reasoned) and Recurrent Neural Networks (RNNs). VADER is the lexicon and rule-based sentiment analysis model that predicts the sentiments extracted from input datasets and it is used for training. The feature extraction technique is term-frequency and inverse document frequency. Word-Level Embeddings (WLE) and Character-Level Embeddings (CLE) are the two models that increase the short text and single-word analysis. The proposed model was applied to four real-time datasets: Amazon, eBay, Trip-advisor, and IMDB Movie Reviews. The performance is analyzed using various parameters such as sensitivity, specificity, precision, accuracy, and F1-score.

Short Text Clustering Algorithms, Application and Challenges: A Survey

The number of online documents has rapidly grown, and with the expansion of the Web, document analysis, or text analysis, has become an essential task for preparing, storing, visualizing and mining documents. The texts generated daily on social media platforms such as Twitter, Instagram and Facebook are vast and unstructured. Most of these generated texts come in the form of short text and need special analysis because short text suffers from lack of information and sparsity. Thus, this topic has attracted growing attention from researchers in the data storing and processing community for knowledge discovery. Short text clustering (STC) has become a critical task for automatically grouping various unlabelled texts into meaningful clusters. STC is a necessary step in many applications, including Twitter personalization, sentiment analysis, spam filtering, customer reviews and many other social network-related applications. In the last few years, the natural-language-processing research community has concentrated on STC and attempted to overcome the problems of sparseness, dimensionality, and lack of information. We comprehensively review various STC approaches proposed in the literature. Providing insights into the technological component should assist researchers in identifying the possibilities and challenges facing STC. To gain such insights, we review various literature, journals, and academic papers focusing on STC techniques. The contents of this study are prepared by reviewing, analysing and summarizing diverse types of journals and scholarly articles with a focus on the STC techniques from five authoritative databases: IEEE Xplore, Web of Science, Science Direct, Scopus and Google Scholar. This study focuses on STC techniques: text clustering, challenges to short texts, pre-processing, document representation, dimensionality reduction, similarity measurement of short text and evaluation.

Use of Neural Topic Models in conjunction with Word Embeddings to extract meaningful topics from short texts

Unsupervised machine learning is utilized as a part of the process of topic modeling to discover dormant topics hidden within a large number of documents. The topic model can help with the comprehension, organization, and summarization of large amounts of text. Additionally, it can assist with the discovery of hidden topics that vary across different texts in a corpus. Traditional topic models like pLSA (probabilistic latent semantic analysis) and LDA suffer performance loss when applied to short-text analysis caused by the lack of word co-occurrence information in each short text. One technique being developed to solve this problem is pre-trained word embedding (PWE) with an external corpus used with topic models. These techniques are being developed to perform interpretable topic modeling on short texts. Deep neural networks (DNN) and deep generative models have recently advanced, allowing neural topic models (NTM) to achieve flexibility and efficiency in topic modeling. There have been few studies on neural-topic models with pre-trained word embedding for producing significant topics from short texts. An extensive study with five NTMs was accomplished to test the efficacy of additional PWE in generating comprehensible topics through experiments with different datasets in Arabic and French concerning Moroccan news published on Facebook pages. Several metrics, including topic coherence and topic diversity, are utilized in the process of evaluating the extracted topics. Our research shows that the topic coherence of short texts can be significantly improved using a word embedding with an external corpus.

ГАЛИЦЬКА ШЕВЧЕНКІЯНА: видання збірки поезій “Кобзар” у 20– 30-х рр. ХХ ст.

The present study is dedicated to the publications of works of the national Prophet Taras Shevchenko in Galicia. The authors have attempted to explore the repertoire of Galician Shevchenkiana, provide a short objective text analysis of these publications, establish the problems haunting the leading regional Galician publishers when publishing Ukrainian books under the Polish occupation of the Western Ukraine, particularly Eastern Galicia (the territory of the annexed Western-Ukrainian People’s Republic), compare them with works of some other contemporaries and the textual problems of Shevchenko Studies.

Biterm topic modelling of responses to open-ended questions: A study with US consumers about vertical farming

The aim of the present work was to explore the potential of Biterm Topic Modelling (BTM) for analysing responses to open-ended survey questions in the pursuit of consumer insights. The selection of BTM was based on its suitability to the analysis of short texts compared to other approaches such as Latent Dirichlet Allocation. The empirical context was vertical farming (VF), which participants read a short text about and then answered a question about interest in buying fruits and vegetables from VF. The data came from US consumers (n = 1803) who provided answers with a median length of 9 words. Results were promising about the potential of BTM to uncover latent topics from responses to open-ended questions. The models predicted coherent and consistent topics relating to VF, including buying VF produce or not and year-round fruit and vegetable supply. Two variants of the text about VF were used (n ∼ 900 per variant), and BTM models trained on responses to the variant which emphasised the possibility of using genetic engineering in VF consistently predicted topics related to genetic engineering. Models trained on responses to the variant which emphasized urban production and reduction of carbon emissions linked to product transportation, consistently revealed topics associated to production, environment, and local farming. The major limitation was not taking account of sentiment in consumers’ responses, an issue that BTM shares with other topic models. This is a significant hindrance in the efforts to rely on machine learning for consumer insights.

Investigating the Efficient Use of Word Embedding with Neural-Topic Models for Interpretable Topics from Short Texts.

With the rapid proliferation of social networking sites (SNS), automatic topic extraction from various text messages posted on SNS are becoming an important source of information for understanding current social trends or needs. Latent Dirichlet Allocation (LDA), a probabilistic generative model, is one of the popular topic models in the area of Natural Language Processing (NLP) and has been widely used in information retrieval, topic extraction, and document analysis. Unlike long texts from formal documents, messages on SNS are generally short. Traditional topic models such as LDA or pLSA (probabilistic latent semantic analysis) suffer performance degradation for short-text analysis due to a lack of word co-occurrence information in each short text. To cope with this problem, various techniques are evolving for interpretable topic modeling for short texts, pretrained word embedding with an external corpus combined with topic models is one of them. Due to recent developments of deep neural networks (DNN) and deep generative models, neural-topic models (NTM) are emerging to achieve flexibility and high performance in topic modeling. However, there are very few research works on neural-topic models with pretrained word embedding for generating high-quality topics from short texts. In this work, in addition to pretrained word embedding, a fine-tuning stage with an original corpus is proposed for training neural-topic models in order to generate semantically coherent, corpus-specific topics. An extensive study with eight neural-topic models has been completed to check the effectiveness of additional fine-tuning and pretrained word embedding in generating interpretable topics by simulation experiments with several benchmark datasets. The extracted topics are evaluated by different metrics of topic coherence and topic diversity. We have also studied the performance of the models in classification and clustering tasks. Our study concludes that though auxiliary word embedding with a large external corpus improves the topic coherency of short texts, an additional fine-tuning stage is needed for generating more corpus-specific topics from short-text data.

Development of Training Videos Based on Virtual Reality Side-Cut High-Simulation Simulator of Human Wound Technology and Sealed Sputum Suction.

The development of information technology and the advancement of the process of educational informatization have provided technical support for education and education reform. The virtual simulation teaching mode is no longer a new thing for people, and it is more and more accepted by people familiar with it. Induction and analysis of short message texts generated by students' online learning can fully understand students, make effective adjustments to the classroom, guide teachers' teaching practice, and optimize the classroom, thereby improving students' learning ability, practical ability, innovation ability, and collaboration. To study the effect of virtual simulation education on improving the skills of medical students, this paper is based on video training and education of virtual reality side-cut high-simulation simulator using case analysis and literature analysis methods. It collects data from databases and builds on online education. The model was developed, and a large number of relevant pieces of literature were read and analyzed through the literature survey method. The research results show that virtual simulation teaching can effectively improve students' technical thinking and ability. Students' technical thinking and ability are about 30% higher than traditional teaching methods, and the cooperation consciousness between students reaches 0.8 consciousness, which can solve the contradiction between popularization and improvement. And to solve the problems of polarization and transformation of underachievers, students' personalities can be fully displayed and developed, and education and teaching will be on the track of quality education. This shows that training videos based on virtual reality technology can play a very good role in improving students' technical mastery.

A multi domains short message sentiment classification using hybrid neural network architecture

Sentiment analysis of short texts is challenging because of its limited context of information. It becomes more challenging to be done on limited resource language like Bahasa Indonesia. However, with various deep learning techniques, it can give pretty good accuracy. This paper explores several deep learning methods, such as multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), and builds combinations of those three architectures. The combinations of those three architectures are intended to get the best of those architecture models. The MLP accommodates the use of the previous model to obtain classification output. The CNN layer extracts the word feature vector from text sequences. Subsequently, the LSTM repetitively selects or discards feature sequences based on their context. Those advantages are useful for different domain datasets. The experiments on sentiment analysis of short text in Bahasa Indonesia show that hybrid models can obtain better performance, and the same architecture can be directly used in another domain-specific dataset.

Sentiment Analysis Based on Movie Reviews using Various Classification Techniques : A Review

Sentimental analysis is also called "opinion mining" analyses attitudes and classifies text views. It relates to the use of natural language processing, text, and linguistic processing. A huge amount of data is created with the rapid growth of web technologies. Social networking sites are now popular and normal places where feelings can be shared by short messages. These sentiments involve happiness, sadness, anxiety, fear, etc. The analysis of short texts tends to recognize the crowd's sentiment. Sentiment Analysis on IMDb moviereviews describes a reviewer's general feeling or impression of a movie. Since the perceptions of humans improve the effectiveness of products & since a movie'ssuccess or failure depending on its review, costs are rising, and a good sentiment analysis model needs to be developed, that classifies moviereviews. Machine learning methods use ML algorithms to carry out sentiment analysis as a standard classification problem using syntactic and language characteristics. There are some methods of machine learning used for sentiment analysis in this paper. Most of the sentiment analysis is performed using SVM, RF, ANN, and NB, Algorithms of DT, BN, & KNN.