Text Length Research Articles

Natural language processing for automated triage and prioritization of individual case safety reports for case-by-case assessment

Objective: To improve a previously developed prediction model that could assist in the triage of individual case safety reports using the addition of features designed from free text fields using natural language processing.Methods: Structured features and natural language processing (NLP) features were used to train a bagging classifier model. NLP features were extracted from free text fields. A bag-of-words model was applied. Stop words were deleted and words that were significantly differently distributed among the case and non-case reports were used for the training data. Besides NLP features from free-text fields, the data also consisted of a list of signal words deemed important by expert report assessors. Lastly, variables with multiple categories were transformed to numerical variables using the weight of evidence method.Results: the model, a bagging classifier of decision trees had an AUC of 0.921 (95% CI = 0.918–0.925). Generic drug name, info text length, ATC code, BMI and patient age. were most important features in classification.Conclusion: this predictive model using Natural Language Processing could be used to assist assessors in prioritizing which future ICSRs to assess first, based on the probability that it is a case which requires clinical review.

Ecological diversity methods improve quantitative examination of student language in short constructed responses in STEM

We novelly applied established ecology methods to quantify and compare language diversity within a corpus of short written student texts. Constructed responses (CRs) are a common form of assessment but are difficult to evaluate using traditional methods of lexical diversity due to text length restrictions. Herein, we examined the utility of ecological diversity measures and ordination techniques to quantify differences in short texts by applying these methods in parallel to traditional text analysis methods to a corpus of previously studied college student CRs. The CRs were collected at two time points (Timing), from three types of higher-ed institutions (Type), and across three levels of student understanding (Thinking). Using previous work, we were able to predict that we would observe the most difference based on Thinking, then Timing and did not expect differences based on Type allowing us to test the utility of these methods for categorical examination of the corpus. We found that the ecological diversity metrics that compare CRs to each other (Whittaker’s beta, species turnover, and Bray–Curtis Dissimilarity) were informative and correlated well with our predicted differences among categories and other text analysis methods. Other ecological measures, including Shannon’s and Simpson’s diversity, measure the diversity of language within a single CR. Additionally, ordination provided meaningful visual representations of the corpus by reducing complex word frequency matrices to two-dimensional graphs. Using the ordination graphs, we were able to observe patterns in the CR corpus that further supported our predictions for the data set. This work establishes novel approaches to measuring language diversity within short texts that can be used to examine differences in student language and possible associations with categorical data.

Rainstorm-Induced Emergency Recognition from Citizens’ Communications Based on Spatial Feature Extraction and Transfer Learning

The rapid recognition of rainstorm-induced emergencies (e.g., building and road inundation, facility damage, and trapped citizens) is vital to timely disaster response. One big challenge that limits the performance of emergency recognition is the data imbalance between different emergency domains. The present study aims to develop an effective cross-domain transfer learning framework for rainstorm-induced emergency recognition based on the text reports provided by citizens. The critical component of the framework is the use of joint distribution adaption (JDA) analysis embedded in a discriminative feature mapping procedure, which transfers rich knowledge learned from large-scale datasets to the learning task from small emergence data. Considering the feature incompleteness that is caused by short text length, a basic probability assignment function is constructed and applied to extract important spatial features for rainstorm emergency recognition, with an improved marginal Fisher analysis being adopted to optimize cross-domain text feature representation. The proposed scheme is validated using the empirical data of ten emergency classes from Wuhan City, China. Our experimental results show that the proposed method could significantly address data imbalance and thus help achieve high recognition performance through domain knowledge complementation. Meanwhile, the use of various spatial features is proved to be effective in tackling missing features. This scheme can be further developed into smart systems for rainstorm disaster response with reasonable performance and imbalanced sample sizes.

Conscientiousness and Performance: The Influence of Personality on Investment Decisions

We extract proxies for trader conscientiousness from plain text to explain the cross-section of individual and institutional trader performance. The literature claims conscientiousness to be a main determinant of workplace performance. We employ measures like text length, error frequency, sentence simplicity, and lexical diversity to construct a conscientiousness index. Our findings suggest that more conscientious traders outperform their peers on a risk-adjusted basis. This implies that personality affects investment decisions. Our data stems from a web-based platform that gives individuals the opportunity to set up small investment funds other users can invest in.

Corpus-based bundle analysis to disciplinary variations: Relocating the role of bundle extraction criteria

Previous lexical bundle research has stimulated heated discussions on disciplinary variations and disciplinary specificity-generality spectrum. The current study explores whether (and how) bundle extraction criteria (i.e. frequency, dispersion, and bundle length) may affect the conclusions on disciplinary variations and specificity-generality. Focusing on eight disciplines, it used an 11-million corpus of academic journal articles with a balanced design (the same number of texts and similar average text length for each subcorpus). The results indicated a clear picture of disciplinary variations and a strong tendency towards disciplinary specificity. More importantly, the results suggested that different methodological criteria played an important part, especially concerning the analysis of disciplinary specificity or generality. The choice of ‘4-word’ bundles over ‘3-word’ bundles, in particular, would tend to be associated with a result of a higher degree of disciplinary specificity. Regarding disciplinary variations, it was found that the effect from different choices of bundle extraction criteria was relatively smaller. Only the choice on different dispersion requirements could predict the significant differences between certain disciplines. These findings provide support for disciplinary variations and new perspectives on the disciplinary specificity-generality debate.

UNLOCKING CUSTOMER SENTIMENT INSIGHTS WITH AZURE SENTIMENT ANALYSIS: A COMPREHENSIVE REVIEW AND ANALYSIS

The paper analyzes the accuracy of the Azure Sentiment Analysis service for five languages, namely Romanian, French, Italian, Portuguese, and Spanish. The study generated 300 texts for each language type expressing positive and negative sentiments with varying lengths (less than 100 characters, between 100 and 250 characters, and more than 250 characters). The Azure Sentiment Analysis Review custom-made application was developed using C# language with .NET Framework and Entity Framework for the Microsoft SQL database, and it is used to make a request to the Azure Sentiment Service, and the response sets the label into the database. The expected and Azure labels for each type of analyzed text were described as well. The accuracy of sentiment recognition for different languages and text lengths is presented in the form of statistics, with the global accuracy of the service being 81.8%. The challenges of accurately classifying the sentiment of short and long texts were highlighted. The results suggest that texts of moderate length are easier to classify.

Рукописный текст садханы «Юток-ньинтик» Халха Дамцик Дордже из тибетского фонда Центра восточных рукописей и ксилографов Института монголоведения, буддологии и тибетологии Сибирского отделения РАН. XIX в.

The study of the written heritage of prominent Buddhist figures in Mongolia and Buryatia is an important area of research for Russian centers in the field of Tibetology and Mongolian studies, as it provides correct understanding and objective evaluation of all aspects of spiritual life of the Mongolian-speaking peoples and interaction of Mongolian-Tibetan cultural traditions. The present study is relevant because, in the Russian oriental studies, works considering texts from the cycle of medical teachings gYu thog snying thig, compiled by Mongolian authors, are almost non-existent. The main purpose of this article is source analysis of the work called bDud rtsi'i snying po (gYu thog snying thig rigs bsdus kyi sgrub thabs bdud rtsi'i snying po), the authorship of which is attributed to the Mongolian Buddhist figure Khalkha Damtsik Dorje (Khal kha dam tshig rdo rje, 1781–1855). In Western and Russian Tibetology, this work has not yet been specially studied. The study has used the handwritten version of this work, stored in the medical collection of the Tibetan fond of the Centre of Oriental Manuscripts and Xylographs of the Institute for Mongolian, Buddhist, and Tibetan studies at the Siberian Branch of the Russian Academy of Sciences (COMX IMBT RAS). The article shows the particularity of texts created by Tibetan masters over the centuries and included in the gYu thog snying thig’s rich anthology, which we tentatively divide into three parts: Buddhist, medical, and ritual texts. According to our classification, the considered work bDud rtsi'i snying po belongs to the first group of texts, more specifically, to the practice of the “three roots” (rtsa ba gsum) of the generation stage (skyed rim): Outer, Inner, and Secret Guru Yoga practice. The composition is written in the s?dhana genre for the cycle of medical teachings gYu thog snying thig and has a structure corresponding to it: the preliminary part (taking refuge, the development of bodhichitta), the main part (visualization of the buddhas and ??ki??s, repeating the mantra), and the final part (dedication of merit to all living beings). The article shows that bDud rtsi'i snying po is an abridged version of the dPag bsam ljon ?bras s?dhana (gYu thog snying thig gi sgrub thabs rgyun ?khyer dpag bsam ljon ?bras), included by Khalkha Damtsik Dorje in the 10th volume of the collected works (gsung ‘bum). It has been established that these two versions differ only in text length and certain features in the description of some parts of the practice. A comparative analysis of key elements in the content of extensive and abbreviated s?dhana versions is provided. The study of these two s?dhanas proves that the author of the bDud rtsi'i snying po was Khalkha Damtsik Dorje. The introduction into scientific use of this previously unknown work of Khalkha Damtsik Dorje, found in the Tibetan fund of the COMX IMBT RAS, enriches the source base of modern research in the field of traditional spiritual practices and history of the development of Buddhism and Tibetan medicine in Mongolia and Tibet in the 19th century.

Who Tells Your Story? Analyzing a Century of Utah History

Who Tells Your Story? Analyzing a Century of Utah History

A New Speech Encoder Based on Dynamic Framing Approach

Latent information is difficult to get from the text in speech synthesis. Studies show that features from speech can get more information to help text encoding. In the field of speech encoding, a lot of work has been conducted on two aspects. The first aspect is to encode speech frame by frame. The second aspect is to encode the whole speech to a vector. But the scale in these aspects is fixed. So, encoding speech with an adjustable scale for more latent information is worthy of investigation. But current alignment approaches only support frame-by-frame encoding and speech-to-vector encoding. It remains a challenge to propose a new alignment approach to support adjustable scale speech encoding. This paper presents the dynamic speech encoder with a new alignment approach in conjunction with frame-by-frame encoding and speech-to-vector encoding. The speech feature from our model achieves three functions. First, the speech feature can reconstruct the origin speech while the length of the speech feature is equal to the text length. Second, our model can get text embedding from speech, and the encoded speech feature is similar to the text embedding result. Finally, it can transfer the style of synthesis speech and make it more similar to the given reference speech.

Emotion Classification in Texts Over Graph Neural Networks: Semantic Representation is Better Than Syntactic

Social media is a widely used platform that provides a huge amount of user-generated content that can be processed to extract information about users’ emotions. This has numerous benefits, such as understanding how individuals feel about certain news or events. It can be challenging to categorize emotions from text created on social media, especially when trying to identify several different emotions from a short text length, as in a multi-label classification problem. Most previous work on emotion classification has focused on deep neural networks such as Convolutional Neural Networks and Recurrent Neural Networks. However, none of these networks have used semantic and syntactic knowledge to classify multiple emotions from a text. In this study, semantic and syntactic aware graph attention networks were proposed to classify emotions from a text with multiple labels. We integrated semantic information in the graph attention network in the form of Universal Conceptual Cognitive Annotation and syntactic information in the form of dependency trees. Our extensive experimental results showed that our two models, UCCA-GAT (accuracy = 71.2) and Dep-GAT (accuracy = 68.7), were able to outperform the state-of-the-art performance on both the challenging SemEval-2018 E-c: Detecting Emotions (multi-label classification) English dataset (accuracy = 58.8) and GoEmotions dataset (accuracy = 65.9).

Information Hiding Method For Gray Images Using Motif Patterns

Information hiding is one of multimedia security tasks need to develop and update in Continuously. Thus, the researchers work in this field and interest in developing and improving the information hiding techniques. In this paper, a new method for develop least significant bits (LSB) method is introduced. The method includes a schema for hiding two bits of secret text in each pixel (least and penultimate bits of pixel) in gray image considering motif Z, U, N, and C patterns. The method is implemented on different standard images with size 512*512 and hide different secret text lengths. The experimental and results show the efficiency of method that hide two bits in each pixel compare with the traditional LSB method that hide one bit of data in each pixel of image. The results show that the proposed method produces a good accuracy of stego image near to the original LSB method in terms of PSNR accuracy metric.

PI-Link: A Ground-Truth Dataset of Links Between Pull-Requests and Issues in GitHub

GitHub hosts Git repositories and provides issues-tracking services to provide a better collaboration environment for software developers. Issues and Pull-Requests are frequently used in GitHub to discuss and review the software requirements (new features, bugs, etc.) and software solutions (source code, test cases, etc.) respectively. The links between Issues and their corresponding Pull-Requests comprise valuable information to keep tracking current development as well as documenting knowledge for future development. Considering a large number of links, such information can be used to train machine learning models for several purposes such as feature location, bug prediction and localization, recommendation systems and documentation generation. To the best of our knowledge, no dataset has been proposed as a ground-truth of links between Issues and Pull-Requests. In this paper, we propose, PI-Link, a new significant and reliable ground-truth dataset composed of 50369 links that explicitly connect 34732 Issues with 50369 Pull-Requests. These links are automatically extracted from all (907,139) Android projects in GitHub created between January 1, 2011 and January 1, 2021. To better organize and store the collected data, we propose a metamodel based on the concepts of Issues and Pull Requests. Moreover, we analyze the relationships between Issues and their linked Pull Requests based on four features related to their titles, bodies, labels and comments. The selected features are analyzed in terms of their lengths and similarities based on three lexical and one semantic similarity metrics. The results showed promising similarities between Issues and their linked PRs at the lexical and semantic levels. In addition, some feature similarities are sensitive to the text length, whereas other feature similarities are sensitive to the term frequency.

Linguistic Features of Korean EFL Learners’ Writing: Based on Writing Quality and Genre

The present study examines the linguistic features of Korean college students’ English writings in terms of their writing quality and genre. Forty-eight Korean college students took part in the study, and their writing samples, comprised of narrative and exposition compositions, were collected to analyze on the basis of fluency and syntactic complexity. A total of 95 writings were entered into the computer program L2 syntactic complexity analyzer (L2SCA), and then statistical analyses such as ANOVA and t-test were performed to investigate how the linguistic features of the participants’ English writings are different depending on their writing quality and genre. The results showed that participants’ writing quality had a statistically significant impact on the text length of their writings, while it did not have a statistically significant effect on 13 measures out of 14 syntactic complexity measures. However, the results of genre differences indicated that the genre of writing had a substantial impact on 15 measures including fluency and syntactic complexity in the participants’ writing. Based on the results, some implications on how English writing instruction can better help Korean learners develop their English writing skills are discussed in the end.

Readability Assessment of Reading Texts in Pathway to English for SMA/MA Grade X

The purpose of the study is to describe readability of reading texts in textbook, ‘Pathway to English’ for SMA/MA Grade X’ published by Erlangga. The study is a quantitative content analysis. The source of the data was the textbook, and only reading texts with minimally 150 words in length were taken as the sample. 22 reading texts that matched the criteria were analyzed quantitatively in percentage form. Result of the data analysis shows that reveals that 9 (or 41%) reading texts match tenth grade level, but the rest, 4 (or 18%) reading texts are to easy, at 7th-8th grade level. and 9 (or 41%) reading texts are are fairly difficult to difficult, at 11th-16th grade level. Put it another way, 59% reading texts with minimally 150 words in length selected for use in EFL textbook ‘Pathway to English’ published by Penerbit Erlangga in 2016 were not in accordance with tenth grade SMA students’ readability level. In addition, It was also found that the data show that readability level of a text do not depend on text length.

Development of clinical vignettes to assess healthcare decision-making capacity in elderly with mild cognitive impairment and Alzheimer's disease

IntroductionCognitive impairment can constrict healthcare decision-making capacity, as it affects the ability to understand, appreciate, and reason with information, as well as communication abilities. Therefore, decision-making capacity of elders with mild cognitive impairment or Alzheimer's disease should be carefully assessed when patients are asked to make decisions regarding their health. Vignettes are particularly relevant to assess healthcare decision capacity, since they can come close to real life situations and improve statistical reliability of capacity assessment instruments. ObjectiveThis paper describes the construction and development process of three hypothetical vignettes, to be included in a new Portuguese assessment tool of healthcare decision-making capacity (CAI-Health). MethodFor vignettes’ development, examples from other assessment tools were first reviewed to summarize their text length, language complexity and health information contained. Most prevalent causes of mortality and morbidity in Portuguese elders were then identified, in order to select the health issues to include in CAI-Health’ vignettes. Seven vignettes were developed, and three were selected to be included in CAI-Health. After vignette's selection, these were reviewed by three experienced medical experts, during a focus group. ConclusionVignettes final version include cases of increased complexity, presenting situations of mild cognitive impairment, lung tumor and knee arthrosis.

Comparative analysis of new meta-heuristic-variants for privacy preservation in wireless mobile adhoc networks for IoT applications

“Mobile Ad Hoc Network (MANET)” is a self-configurable, self-repairing, self-maintaining, highly mobile, decentralized, and independent wireless network, which has the liberty to move from one to another place. Such networks do not have any pre-existing infrastructure. The adoption of a smart environment in MANET requires new protocols to connect the gadgets to the internet. A smart environment with routing protocols should assure the following properties like connectivity among the nodes, “Quality of Service (QoS)”, and fairness, both in access points and ad-hoc networks. Combination with the Internet of Things (IoT) and MANET generates a novel MANET-IoT system, which focuses on reducing the implementing costs of the network and providing better mobility for users. The necessity of these integrated networks is increasing in military operations, rescue operations, personal area networks, emergency rooms, and meeting rooms. Routing in MANETs is a not simple job and has projected a huge range of attention from researchers around the world. Thus, the intention of this task is a development of a security protocol in MANET for the IoT platform. For dealing with encryption and decryption strategies to handle MANET and IoT data, a new approach is suggested through the enhanced chaotic map. Here, three improved algorithms are implemented for proposing the optimized key management scheme under a chaotic map, which is the Modified Updating-based Harris Hawks Optimization Algorithm (MU-HHO), Mean Solution-based Averaging Sailfish Optimizer (MS-ASFO), Adaptive Basic Reproduction Rate-based Coronavirus Herd Immunity Optimizer (ABRR-CHIO). In the convergence evaluation, while taking the length of plain text as 40, ABRR-CHIO shows superior performance over other techniques at the 60th iteration, which is 96%, 95%, 93%, 96%, and 80% superior to HHO, SFO, CHIO, SA-SFO, and CHHSO. Finally, the performance evaluation is performed regarding “statistical analysis, convergence analysis, and communication overhead” to reveal the superiority of the designed model.

On the Hardness of Sequence Alignment on De Bruijn Graphs.

The problem of aligning a sequence to a walk in a labeled graph is of fundamental importance to Computational Biology. For an arbitrary graph and a pattern P of length m, a lower bound based on the Strong Exponential Time Hypothesis implies that an algorithm for finding a walk in G exactly matching P significantly faster than time is unlikely. However, for many special graphs, such as de Bruijn graphs, the problem can be solved in linear time. For approximate matching, the picture is more complex. When edits (substitutions, insertions, and deletions) are only allowed to the pattern, or when the graph is acyclic, the problem is solvable in time. When edits are allowed to arbitrary cyclic graphs, the problem becomes NP-complete, even on binary alphabets. Moreover, NP-completeness continues to hold even when edits are restricted to only substitutions. Despite the popularity of the de Bruijn graphs in Computational Biology, the complexity of approximate pattern matching on the de Bruijn graphs remained unknown. We investigate this problem and show that the properties that make the de Bruijn graphs amenable to efficient exact pattern matching do not extend to approximate matching, even when restricted to the substitutions only case with alphabet size four. Specifically, we prove that determining the existence of a matching walk in a de Bruijn graph is NP-complete when substitutions are allowed to the graph. We also demonstrate that an algorithm significantly faster than is unlikely for the de Bruijn graphs in the case where substitutions are only allowed to the pattern. This stands in contrast to pattern-to-text matching where exact matching is solvable in linear time, such as on the de Bruijn graphs, but approximate matching under substitutions is solvable in subquadratic time, where n is the text's length.

BERT- and BiLSTM-Based Sentiment Analysis of Online Chinese Buzzwords

Sentiment analysis of online Chinese buzzwords (OCBs) is important for healthy development of platforms, such as games and social networking, which can avoid transmission of negative emotions through prediction of users’ sentiment tendencies. Buzzwords have the characteristics of varying text length, irregular wording, ignoring syntactic and grammatical requirements, no complete semantic structure, and no obvious sentiment features. This results in interference and challenges to the sentiment analysis of such texts. Sentiment analysis also requires capturing effective sentiment features from deeper contextual information. To solve the above problems, we propose a deep learning model combining BERT and BiLSTM. The goal is to generate dynamic representations of OCB vectors in downstream tasks by fine-tuning the BERT model and to capture the rich information of the text at the embedding layer to solve the problem of static representations of word vectors. The generated word vectors are then transferred to the BiLSTM model for feature extraction to obtain the local and global semantic features of the text while highlighting the text sentiment polarity for sentiment classification. The experimental results show that the model works well in terms of the comprehensive evaluation index F1. Our model also has important significance and research value for sentiment analysis of irregular texts, such as OCBs.

Structured abstract summarization of scientific articles: Summarization using full‐text section information

AbstractThe automatic summarization of scientific articles differs from other text genres because of the structured format and longer text length. Previous approaches have focused on tackling the lengthy nature of scientific articles, aiming to improve the computational efficiency of summarizing long text using a flat, unstructured abstract. However, the structured format of scientific articles and characteristics of each section have not been fully explored, despite their importance. The lack of a sufficient investigation and discussion of various characteristics for each section and their influence on summarization results has hindered the practical use of automatic summarization for scientific articles. To provide a balanced abstract proportionally emphasizing each section of a scientific article, the community introduced the structured abstract, an abstract with distinct, labeled sections. Using this information, in this study, we aim to understand tasks ranging from data preparation to model evaluation from diverse viewpoints. Specifically, we provide a preprocessed large‐scale dataset and propose a summarization method applying the introduction, methods, results, and discussion (IMRaD) format reflecting the characteristics of each section. We also discuss the objective benchmarks and perspectives of state‐of‐the‐art algorithms and present the challenges and research directions in this area.

Linguistic anomalies in the language of patients with schizophrenia

In terms of thought disorder, the language of patients with schizophrenia itself could be a valuable resource. Some valuable studies on the language of patients with schizophrenia have been performed. However, most such studies have been confined to English-speaking countries, or at least those where Indo-European languages are spoken. Therefore, we investigated linguistic anomalies in the language of Korean patients with schizophrenia. Short texts written by 69 patients with schizophrenia from a single mental hospital and matched normal control participants were analyzed. We evaluated these texts in terms of semantic and syntactic errors. Then, we compared the error rates adjusted for text length between patients and normal control participants. We also divided the patients with schizophrenia into two groups by their duration of illness and compared these two groups to investigate the relationship between the duration of illness and linguistic anomalies. The patients with schizophrenia committed a total of 1.86 (2.52) semantic errors and 1.37 (1.79) syntactic errors per 100 characters, which were significantly more frequent than errors committed by normal control participants. Furthermore, there was a notably high number of semantic errors relative to syntactic errors in the language of patients with schizophrenia. Our study results are consistent with previous studies from English-speaking countries, implying that the linguistic anomalies of patients with schizophrenia are not confined to a single language. Because language is essential in mental function, further research on linguistic anomalies in patients with schizophrenia is recommended.