Use Of Textual Data Research Articles

Nbias: A natural language processing framework for BIAS identification in text

Bias in textual data can lead to skewed interpretations and outcomes when the data is used. These biases could perpetuate stereotypes, discrimination, or other forms of unfair treatment. An algorithm trained on biased data may end up making decisions that disproportionately impact a certain group of people. Therefore, it is crucial to detect and remove these biases to ensure the fair and ethical use of data. To this end, we develop a comprehensive and robust framework Nbias that consists of four main layers: data, corpus construction, model development and an evaluation layer. The dataset is constructed by collecting diverse data from various domains, including social media, healthcare, and job hiring portals. As such, we applied a transformer-based token classification model that is able to identify bias words/phrases through a unique named entity BIAS. In the evaluation procedure, we incorporate a blend of quantitative and qualitative measures to gauge the effectiveness of our models. We achieve accuracy improvements ranging from 1% to 8% compared to baselines. We are also able to generate a robust understanding of the model functioning. The proposed approach is applicable to a variety of biases and contributes to the fair and ethical use of textual data.

Representing and utilizing clinical textual data for real world studies: An OHDSI approach

Clinical documentation in electronic health records contains crucial narratives and details about patients and their care. Natural language processing (NLP) can unlock the information conveyed in clinical notes and reports, and thus plays a critical role in real-world studies. The NLP Working Group at the Observational Health Data Sciences and Informatics (OHDSI) consortium was established to develop methods and tools to promote the use of textual data and NLP in real-world observational studies. In this paper, we describe a framework for representing and utilizing textual data in real-world evidence generation, including representations of information from clinical text in the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), the workflow and tools that were developed to extract, transform and load (ETL) data from clinical notes into tables in OMOP CDM, as well as current applications and specific use cases of the proposed OHDSI NLP solution at large consortia and individual institutions with English textual data. Challenges faced and lessons learned during the process are also discussed to provide valuable insights for researchers who are planning to implement NLP solutions in real-world studies.

Pet analytics: Predicting adoption speed of pets from their online profiles

Many animals are put up for adoption. In turn, having many available animals can overburden shelters if this number rises above a shelter’s maximum capacity. Pet adoption websites need to identify which characteristics or general information about the animals are most salient to potential pet adopters to increase adoption speed and avoid overcrowding. To solve this problem, we have applied several data mining techniques including regression, decision tree, random forest, gradient boosting, and neural network to find which technique is best at predicting adoption speed (a.k.a. length of stay - LOS), and which variable(s) are considered significant. We applied topic modeling techniques to discover latent features using information extracted from description scripts and fed them into our predictive models. Our ensemble model produced an impressive average squared error (ASE) of 1.15584 weeks. While the use of textual data helped improve the performance of regression and gradient boosting models, other models did not receive any additional benefit from textual data. Our results indicated that pet characteristics such as age, breed, quantity, and sterilization status are key factors that influence adoption speed. This study could further help shelters around the world be able to optimize their adoption process.

Forecasting Corporate Failure in the Chinese Energy Sector: A Novel Integrated Model of Deep Learning and Support Vector Machine

Accurate forecasts of corporate failure in the Chinese energy sector are drivers for both operational excellence in the national energy systems and sustainable investment of the energy sector. This paper proposes a novel integrated model (NIM) for corporate failure forecasting in the Chinese energy sector by considering textual data and numerical data simultaneously. Given the feature of textual data and numerical data, convolutional neural network oriented deep learning (CNN-DL) and support vector machine (SVM) are employed as the base classifiers to forecast using textual data and numerical data, respectively. Subsequently, soft set (SS) theory is applied to integrate outputs of CNN-DL and SVM. Hence, NIM inherits advantages and avoids disadvantages of CNN-DL, SVM, and SS. It is able to improve the forecasting performance by taking full use of textual data and numerical data. For verification, NIM is applied to the real data of Chinese listed energy firms. Empirical results indicate that, compared with benchmarks, NIM demonstrates superior performance of corporate failure forecasting in the Chinese energy sector.

Combining different evaluation systems on social media for measuring user satisfaction

Web 2.0 allows people to express and share their opinions about products and services they buy/use. These opinions can be expressed in various ways: numbers, texts, emoticons, pictures, videos, audios, and so on. There has been great interest in the strategies for extracting, organising and analysing this kind of information. In a social media mining framework, in particular, the use of textual data has been explored in depth and still represents a challenge. On a rating and review website, user satisfaction can be detected both from a rating scale and from the written text. However, in common practice, there is a lack of algorithms able to combine judgments provided with both comments and scores. In this paper we propose a strategy to jointly measure the user evaluations obtained from the two systems. Text polarity is detected with a sentiment-based approach, and then combined with the associated rating score. The new rating scale has a finer granularity. Moreover, also enables the reviews to be ranked. We show the effectiveness of our proposal by analysing a set of reviews about the Uffizi Gallery in Florence (Italy) published on TripAdvisor.

The Textual Criticism of Middle English Manuscript Traditions: A Survey of Critical Issues in the Interpretation of Textual Data

This essay is intended to survey two broad issues which determine the use of textual data. The first is the underlying orientation towards the use of textual data and how this relates to critical evaluations of agency, authority and materiality. This essay surveys two broad orientations: (i) an essentially retrospective genetic orientation and, (ii) an orientation which focuses on the phenomenon of change. Both approaches are dependent on the ability to distinguish original readings from scribal readings, identify genetic relationships and account for acts of horizontal transmission. With this in mind, the second issue with which this essay is concerned is the importance of critical interpretation in the categorisation of textual data. This essay argues that textual criticism is a practical demonstration of the difficulties of interpretation and that no textual data ‘has any real evidential value until it has been interpreted’ (Patterson 90).

An automatic video indexing method based on shot classification

AbstractWith the recent increase in the number of news videos and in their value, their automatic indexing has been anticipated. Among various proposals for this problem, the use of textual data has been actively considered, and some applications of this type have actually been developed. Nonetheless, most of these approaches are textual data oriented, and a few of them consider the correspondences between their indexes (keywords) and image contents which are essentials for an image database.This paper proposes an automatic video indexing method which takes advantage of the characteristic of news videos: similar images have similar contents. The method tags indexes selectively according to typical image content. The method has been applied to actual news videos, and indexing has been successful for between 25% and 93% of “typical shots,” and for between 75% and 100% of “captionized shots.” © 2001 Scripta Technica, Syst Comp Jpn, 32(9): 32–41, 2001

Measuring emotion in open-ended survey responses: An application of textual data analysis

The present study illustrates the use of a qualitative research technique, textual data analysis, in assessing the emotional content of open-ended survey responses. The Dictionary of Affect in Language (DAL), one of many acceptable routes to the measurement of emotion, provided the basis for scoring open-ended responses collected in a study of the organizational transformation efforts of a Fortune 100 firm based in the midwestern United States. Managers and corporate executives were surveyed with an in-depth questionnaire that included quantitative measures of several work-related perceptions and attitudes as well as open-ended questions regarding two major events that occurred during the transformation. Dimension scores produced from the DAL and direct ratings of open-ended responses correlated with the quantitative measures in expected and consistent ways. The use of textual data analytic approaches is discussed, and advantages and disadvantages of such approaches are broadly addressed.

An architecture and design approach for a geographical information retrieval system to support retrieval by content and browsing★

In present Geographical Information Systems (GIS), access to information is restricted to experienced users. On the contrary, it is important to permit to final users, easy access to information by content and in a natural way. In fact, a final user is not always an expert on GIS, but he is an expert in a specific application area, such as urban management or land administration. Geographical systems must be able to manage geographical and structured data, together with textual data, and data in other media. In fact, an active use of textual data can add an effective access point for the collection of geographical information. So, it is necessary to include textual-management operations in currently existing geographical systems, in order to provide a useful and comprehensive access point for geographical information collection to nonexpert users of the application. This paper introduces an architecture and design approach for a Geographical Information Retrieval System (GIRS) capable of supporting retrieval by content and browsing on textual data; the architecture and design approach provides the framework for the management of various kinds of media that are necessary to manage in geographical systems.