Search results

1 – 10 of over 1000
Click here to view access options
Article
Publication date: 28 December 2020

Arpita Gupta, Saloni Priyani and Ramadoss Balakrishnan

In this study, the authors have used the customer reviews of books and movies in natural language for the purpose of sentiment analysis and reputation generation on the…

Abstract

Purpose

In this study, the authors have used the customer reviews of books and movies in natural language for the purpose of sentiment analysis and reputation generation on the reviews. Most of the existing work has performed sentiment analysis and reputation generation on the reviews by using single classification models and considered other attributes for reputation generation.

Design/methodology/approach

The authors have taken review, helpfulness and rating into consideration. In this paper, the authors have performed sentiment analysis for extracting the probability of the review belonging to a class, which is further used for generating the sentiment score and reputation of the review. The authors have used pre-trained BERT fine-tuned for sentiment analysis on movie and book reviews separately.

Findings

In this study, the authors have also combined the three models (BERT, Naïve Bayes and SVM) for more accurate sentiment classification and reputation generation, which has outperformed the best BERT model in this study. They have achieved the best accuracy of 91.2% for the movie review data set and 89.4% for the book review data set which is better than the existing state-of-art methods. They have used the transfer learning concept in deep learning where you take knowledge gained from one problem and apply it to a similar problem.

Originality/value

The authors have proposed a novel model based on combination of three classification models, which has outperformed the existing state-of-art methods. To the best of the authors’ knowledge, there is no existing model which combines three models for sentiment score calculation and reputation generation for the book review data set.

Details

World Journal of Engineering, vol. 18 no. 4
Type: Research Article
ISSN: 1708-5284

Keywords

Click here to view access options
Article
Publication date: 22 October 2021

Na Pang, Li Qian, Weimin Lyu and Jin-Dong Yang

In computational chemistry, the chemical bond energy (pKa) is essential, but most pKa-related data are submerged in scientific papers, with only a few data that have been…

Abstract

Purpose

In computational chemistry, the chemical bond energy (pKa) is essential, but most pKa-related data are submerged in scientific papers, with only a few data that have been extracted by domain experts manually. The loss of scientific data does not contribute to in-depth and innovative scientific data analysis. To address this problem, this study aims to utilize natural language processing methods to extract pKa-related scientific data in chemical papers.

Design/methodology/approach

Based on the previous Bert-CRF model combined with dictionaries and rules to resolve the problem of a large number of unknown words of professional vocabulary, in this paper, the authors proposed an end-to-end Bert-CRF model with inputting constructed domain wordpiece tokens using text mining methods. The authors use standard high-frequency string extraction techniques to construct domain wordpiece tokens for specific domains. And in the subsequent deep learning work, domain features are added to the input.

Findings

The experiments show that the end-to-end Bert-CRF model could have a relatively good result and can be easily transferred to other domains because it reduces the requirements for experts by using automatic high-frequency wordpiece tokens extraction techniques to construct the domain wordpiece tokenization rules and then input domain features to the Bert model.

Originality/value

By decomposing lots of unknown words with domain feature-based wordpiece tokens, the authors manage to resolve the problem of a large amount of professional vocabulary and achieve a relatively ideal extraction result compared to the baseline model. The end-to-end model explores low-cost migration for entity and relation extraction in professional fields, reducing the requirements for experts.

Details

Data Technologies and Applications, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2514-9288

Keywords

Click here to view access options
Book part
Publication date: 20 December 2013

Christine Shearer, Jennifer Bea Rogers-Brown, Karl Bryant, Rachel Cranfill and Barbara Herr Harthorn

Research has found a subgroup of conservative white males have lower perceptions of risk across a variety of environmental and health hazards. Less research has looked at…

Abstract

Research has found a subgroup of conservative white males have lower perceptions of risk across a variety of environmental and health hazards. Less research has looked at the views of these “low risk” individuals in group interactions. Through qualitative analysis of a technology deliberation, we note that white men expressing low risk views regarding technologies for energy and the environment also often express high social risks around potential loss of control. We argue these risk perceptions reflect identification with corporate concerns, usually framed in opposition to government and mirroring arguments made by conservative organizations. We situate these views within the broader cultural struggle over who has the power to name and address risks.

Details

William R. Freudenburg, A Life in Social Research
Type: Book
ISBN: 978-1-78190-734-4

Keywords

Click here to view access options
Article
Publication date: 1 May 2020

Qihang Wu, Daifeng Li, Lu Huang and Biyun Ye

Entity relation extraction is an important research direction to obtain structured information. However, most of the current methods are to determine the relations between…

Abstract

Purpose

Entity relation extraction is an important research direction to obtain structured information. However, most of the current methods are to determine the relations between entities in a given sentence based on a stepwise method, seldom considering entities and relations into a unified framework. The joint learning method is an optimal solution that combines relations and entities. This paper aims to optimize hierarchical reinforcement learning framework and provide an efficient model to extract entity relation.

Design/methodology/approach

This paper is based on the hierarchical reinforcement learning framework of joint learning and combines the model with BERT, the best language representation model, to optimize the word embedding and encoding process. Besides, this paper adjusts some punctuation marks to make the data set more standardized, and introduces positional information to improve the performance of the model.

Findings

Experiments show that the model proposed in this paper outperforms the baseline model with a 13% improvement, and achieve 0.742 in F1 score in NYT10 data set. This model can effectively extract entities and relations in large-scale unstructured text and can be applied to the fields of multi-domain information retrieval, intelligent understanding and intelligent interaction.

Originality/value

The research provides an efficient solution for researchers in a different domain to make use of artificial intelligence (AI) technologies to process their unstructured text more accurately.

Details

Information Discovery and Delivery, vol. 48 no. 3
Type: Research Article
ISSN: 2398-6247

Keywords

Click here to view access options
Article
Publication date: 24 September 2020

Toshiki Tomihira, Atsushi Otsuka, Akihiro Yamashita and Tetsuji Satoh

Recently, Unicode has been standardized with the penetration of social networking services, the use of emojis has become common. Emojis, as they are also known, are most…

Abstract

Purpose

Recently, Unicode has been standardized with the penetration of social networking services, the use of emojis has become common. Emojis, as they are also known, are most effective in expressing emotions in sentences. Sentiment analysis in natural language processing manually labels emotions for sentences. The authors can predict sentiment using emoji of text posted on social media without labeling manually. The purpose of this paper is to propose a new model that learns from sentences using emojis as labels, collecting English and Japanese tweets from Twitter as the corpus. The authors verify and compare multiple models based on attention long short-term memory (LSTM) and convolutional neural networks (CNN) and Bidirectional Encoder Representations from Transformers (BERT).

Design/methodology/approach

The authors collected 2,661 kinds of emoji registered as Unicode characters from tweets using Twitter application programming interface. It is a total of 6,149,410 tweets in Japanese. First, the authors visualized a vector space produced by the emojis by Word2Vec. In addition, the authors found that emojis and similar meaning words of emojis are adjacent and verify that emoji can be used for sentiment analysis. Second, it involves entering a line of tweets containing emojis, learning and testing with that emoji as a label. The authors compared the BERT model with the conventional models [CNN, FastText and Attention bidirectional long short-term memory (BiLSTM)] that were high scores in the previous study.

Findings

Visualized the vector space of Word2Vec, the authors found that emojis and similar meaning words of emojis are adjacent and verify that emoji can be used for sentiment analysis. The authors obtained a higher score with BERT models compared to the conventional model. Therefore, the sophisticated experiments demonstrate that they improved the score over the conventional model in two languages. General emoji prediction is greatly influenced by context. In addition, the score may be lowered due to a misunderstanding of meaning. By using BERT based on a bi-directional transformer, the authors can consider the context.

Practical implications

The authors can find emoji in the output words by typing a word using an input method editor (IME). The current IME only considers the most latest inputted word, although it is possible to recommend emojis considering the context of the inputted sentence in this study. Therefore, the research can be used to improve IME performance in the future.

Originality/value

In the paper, the authors focus on multilingual emoji prediction. This is the first attempt of comparison at emoji prediction between Japanese and English. In addition, it is also the first attempt to use the BERT model based on the transformer for predicting limited emojis although the transformer is known to be effective for various NLP tasks. The authors found that a bidirectional transformer is suitable for emoji prediction.

Details

International Journal of Web Information Systems, vol. 16 no. 3
Type: Research Article
ISSN: 1744-0084

Keywords

Click here to view access options
Article
Publication date: 23 March 2020

Hannah Van Borm, Marlot Dhoop, Allien Van Acker and Stijn Baert

The purpose of this paper is to explore the mechanisms underlying hiring discrimination against transgender men.

Abstract

Purpose

The purpose of this paper is to explore the mechanisms underlying hiring discrimination against transgender men.

Design/methodology/approach

The authors conduct a scenario experiment with final-year business students in which fictitious hiring decisions are made about transgender or cisgender male job candidates. More importantly, these candidates are scored on statements related to theoretical reasons for hiring discrimination given in the literature. The resulting data are analysed using a bivariate analysis. Additionally, a multiple mediation model is run.

Findings

Suggestive evidence is found for co-worker and customer taste-based discrimination, but not for employer taste-based discrimination. In addition, results show that transgender men are perceived as being in worse health, being more autonomous and assertive, and have a lower probability to go on parental leave, compared with cisgender men, revealing evidence for (positive and negative) statistical discrimination.

Social implications

Targeted policy measures are needed given the substantial labour market discrimination against transgender individuals measured in former studies. However, to combat this discrimination effectively, one needs to understand its underlying mechanisms. This study provides the first comprehensive exploration of these mechanisms.

Originality/value

This study innovates in being one of the first to explore the relative empirical importance of dominant (theoretical) explanations for hiring discrimination against transgender men. Thereby, the authors take the logical next step in the literature on labour market discrimination against transgender individuals.

Details

International Journal of Manpower, vol. 41 no. 6
Type: Research Article
ISSN: 0143-7720

Keywords

Click here to view access options
Article
Publication date: 26 July 2021

Pengcheng Li, Qikai Liu, Qikai Cheng and Wei Lu

This paper aims to identify data set entities in scientific literature. To address poor recognition caused by a lack of training corpora in existing studies, a distant…

Abstract

Purpose

This paper aims to identify data set entities in scientific literature. To address poor recognition caused by a lack of training corpora in existing studies, a distant supervised learning-based approach is proposed to identify data set entities automatically from large-scale scientific literature in an open domain.

Design/methodology/approach

Firstly, the authors use a dictionary combined with a bootstrapping strategy to create a labelled corpus to apply supervised learning. Secondly, a bidirectional encoder representation from transformers (BERT)-based neural model was applied to identify data set entities in the scientific literature automatically. Finally, two data augmentation techniques, entity replacement and entity masking, were introduced to enhance the model generalisability and improve the recognition of data set entities.

Findings

In the absence of training data, the proposed method can effectively identify data set entities in large-scale scientific papers. The BERT-based vectorised representation and data augmentation techniques enable significant improvements in the generality and robustness of named entity recognition models, especially in long-tailed data set entity recognition.

Originality/value

This paper provides a practical research method for automatically recognising data set entities in scientific literature. To the best of the authors’ knowledge, this is the first attempt to apply distant learning to the study of data set entity recognition. The authors introduce a robust vectorised representation and two data augmentation strategies (entity replacement and entity masking) to address the problem inherent in distant supervised learning methods, which the existing research has mostly ignored. The experimental results demonstrate that our approach effectively improves the recognition of data set entities, especially long-tailed data set entities.

Click here to view access options
Article
Publication date: 22 May 2020

Yuanxin Ouyang, Hongbo Zhang, Wenge Rong, Xiang Li and Zhang Xiong

The purpose of this paper is to propose an attention alignment method for opinion mining of massive open online course (MOOC) comments. Opinion mining is essential for…

Abstract

Purpose

The purpose of this paper is to propose an attention alignment method for opinion mining of massive open online course (MOOC) comments. Opinion mining is essential for MOOC applications. In this study, the authors analyze some of bidirectional encoder representations from transformers (BERT’s) attention heads and explore how to use these attention heads to extract opinions from MOOC comments.

Design/methodology/approach

The approach proposed is based on an attention alignment mechanism with the following three stages: first, extracting original opinions from MOOC comments with dependency parsing. Second, constructing frequent sets and using the frequent sets to prune the opinions. Third, pruning the opinions and discovering new opinions with the attention alignment mechanism.

Findings

The experiments on the MOOC comments data sets suggest that the opinion mining approach based on an attention alignment mechanism can obtain a better F1 score. Moreover, the attention alignment mechanism can discover some of the opinions filtered incorrectly by the frequent sets, which means the attention alignment mechanism can overcome the shortcomings of dependency analysis and frequent sets.

Originality/value

To take full advantage of pretrained language models, the authors propose an attention alignment method for opinion mining and combine this method with dependency analysis and frequent sets to improve the effectiveness. Furthermore, the authors conduct extensive experiments on different combinations of methods. The results show that the attention alignment method can effectively overcome the shortcomings of dependency analysis and frequent sets.

Details

Information Discovery and Delivery, vol. 50 no. 1
Type: Research Article
ISSN: 2398-6247

Keywords

Click here to view access options
Article
Publication date: 2 July 2018

Stijn Baert, Ann-Sofie De Meyer, Yentl Moerman and Eddy Omey

The purpose of this paper is to study the association between firm size and hiring discrimination against women, ethnic minorities and older job candidates.

Downloads
1111

Abstract

Purpose

The purpose of this paper is to study the association between firm size and hiring discrimination against women, ethnic minorities and older job candidates.

Design/methodology/approach

The authors merge field experimental measures on unequal treatment with firm-level data. The resulting data enable the authors to assess whether discrimination varies by indicators of firm size, keeping other firm characteristics constant.

Findings

In contrast with the theoretical expectations, the authors find no evidence for an association between firm size and hiring discrimination. On the other hand, the authors do find suggestive evidence for hiring discrimination being lower in respect of public or non-profit firms (compared to commercial firms).

Social implications

To effectively combat hiring discrimination, one needs to understand its driving factors. In other words, to design adequate policy actions, targeted to the right employers in the right way, one has to gain insight into when individuals are discriminated in particular, i.e. into the moderators of labour market discrimination. In this study, the authors focus on firm size as a moderator of hiring discrimination.

Originality/value

Former contributions investigated this association within the context of ethnic discrimination only and included hardly any controls for other firm-level drivers of discrimination. The authors are the first to study the heterogeneity in discrimination by firm size with respect to multiple discrimination grounds and control for additional firm characteristics.

Details

International Journal of Manpower, vol. 39 no. 4
Type: Research Article
ISSN: 0143-7720

Keywords

Click here to view access options
Book part
Publication date: 17 January 2009

Kallol Bagchi, Peeter Kirs and Zaiyong Tang

Much attention has been given to adoption and diffusion, defined as the degree of market penetration, of Information and Communications Technologies (ICT) in recent years …

Abstract

Much attention has been given to adoption and diffusion, defined as the degree of market penetration, of Information and Communications Technologies (ICT) in recent years (Carter, Jambulingam, Gupta, & Melone, 2001; Kiiski & Pohjola, 2002; Milner, 2003; Benhabib & Spiegel, 2005). The theory of diffusion of innovations considers how a new idea spreads throughout the market over time. The ability to accurately predict new product diffusion is of concern to designers, marketers, managers, and researchers alike. However, although the diffusion process of new products is generally accepted as following an s-curve pattern, where diffusion starts slowly, grows exponentially, peaks, and then declines (as shown in Fig. 1), there is considerable disagreement about what factors affect diffusion and how to measure diffusion rates (Bagchi, Kirs, & Lopez, 2008).

Details

Advances in Business and Management Forecasting
Type: Book
ISBN: 978-1-84855-548-8

1 – 10 of over 1000