scholarly journals Author Profiling in Informal and Formal Language Scenarios Via Transfer Learning

TecnoLógicas ◽  
2021 ◽  
Vol 24 (52) ◽  
pp. e2166
Author(s):  
Daniel Escobar-Grisales ◽  
Juan Camilo Vásquez-Correa ◽  
Juan Rafael Orozco-Arroyave
Keyword(s):  
Social Media ◽  
Transfer Learning ◽  
Call Center ◽  
Formal Language ◽  
Learning Strategy ◽  
Computer Applications ◽  
Formal Structure ◽  
Language Variety ◽  
Using Data ◽  
Author Profiling

The interest in author profiling tasks has increased in the research community because computer applications have shown success in different sectors such as security, marketing, healthcare, and others. Recognition and identification of traits such as gender, age or location based on text data can help to improve different marketing strategies. This type of technology has been widely discussed regarding documents taken from social media. However, its methods have been poorly studied using data with a more formal structure, where there is no access to emoticons, mentions, and other linguistic phenomena that are only present in social media. This paper proposes the use of recurrent and convolutional neural networks and a transfer learning strategy to recognize two demographic traits, i.e., gender and language variety, in documents written in informal and formal language. The models were tested in two different databases consisting of tweets (informal) and call-center conversations (formal). Accuracies of up to 75 % and 68 % were achieved in the recognition of gender in documents with informal and formal language, respectively. Moreover, regarding language variety recognition, accuracies of 92 % and 72 % were obtained in informal and formal text scenarios, respectively. The results indicate that, in relation to the traits considered in this paper, it is possible to transfer the knowledge from a system trained on a specific type of expressions to another one where the structure is completely different and data are scarcer.

Does Social Media Engagement Translate to Civic Engagement Offline?

2021 ◽  
pp. 089976402199944
Author(s):  
Jaclyn Piatak ◽  
Ian Mikkelsen
Keyword(s):  
Social Media ◽  
Civic Engagement ◽  
Presidential Election ◽  
Civic Participation ◽  
Political Engagement ◽  
Political Campaigns ◽  
The Internet ◽  
Online Engagement ◽  
Informal Volunteering ◽  
Using Data

People increasingly engage in politics on social media, but does online engagement translate to offline engagement? Research is mixed with some suggesting how one uses the internet maters. We examine how political engagement on social media corresponds to offline engagement. Using data following the 2016 U.S. Presidential Election, we find the more politically engaged people are on social media, the more likely they are to engage offline across measures of engagement—formal and informal volunteering, attending local meetings, donating to and working for political campaigns, and voting. Findings offer important nuances across types of civic engagement and generations. Although online engagement corresponds to greater engagement offline in the community and may help narrow generational gaps, this should not be the only means to promote civic participation to ensure all have a voice and an opportunity to help, mobilize, and engage.

scholarly journals Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps

2021 ◽  
Author(s):  
Ali H. Al-Timemy ◽  
Nebras H. Ghaeb ◽  
Zahraa M. Mosa ◽  
Javier Escudero
Keyword(s):  
Transfer Learning ◽  
Learning Strategy ◽  
Clinical Decision ◽  
Topographic Maps ◽  
Computer Assisted ◽  
Clinical Knowledge ◽  
Average Accuracy ◽  
Assisted Diagnosis ◽  
Improved Accuracy ◽  
Fine Tune

Abstract Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.

scholarly journals BeautyNet: Joint Multiscale CNN and Transfer Learning Method for Unconstrained Facial Beauty Prediction

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yikui Zhai ◽  
He Cao ◽  
Wenbo Deng ◽  
Junying Gan ◽  
Vincenzo Piuri ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Classification Accuracy ◽  
Learning Strategy ◽  
State Of The Art ◽  
Activation Function ◽  
Training Data ◽  
Fine Grained ◽  
Pattern Recognition Problem ◽  
Face Features ◽  
Facial Beauty

Because of the lack of discriminative face representations and scarcity of labeled training data, facial beauty prediction (FBP), which aims at assessing facial attractiveness automatically, has become a challenging pattern recognition problem. Inspired by recent promising work on fine-grained image classification using the multiscale architecture to extend the diversity of deep features, BeautyNet for unconstrained facial beauty prediction is proposed in this paper. Firstly, a multiscale network is adopted to improve the discriminative of face features. Secondly, to alleviate the computational burden of the multiscale architecture, MFM (max-feature-map) is utilized as an activation function which can not only lighten the network and speed network convergence but also benefit the performance. Finally, transfer learning strategy is introduced here to mitigate the overfitting phenomenon which is caused by the scarcity of labeled facial beauty samples and improves the proposed BeautyNet’s performance. Extensive experiments performed on LSFBD demonstrate that the proposed scheme outperforms the state-of-the-art methods, which can achieve 67.48% classification accuracy.

Improving sentiment scoring mechanism: a case study on airline services

2018 ◽  
Vol 118 (8) ◽  
pp. 1578-1596 ◽  
Author(s):  
Wandeep Kaur ◽  
Vimala Balakrishnan
Keyword(s):  
Social Media ◽  
Content Type ◽  
Exclamation Mark ◽  
Semantic Orientation ◽  
Social Media Text ◽  
Major Airlines ◽  
Using Data ◽  
Sentiment Score ◽  
Repeated Letter ◽  
Facebook Pages

Purpose The purpose of this paper is to investigate the effect of including letter repetition commonly found within social media text and its impact in determining the sentiment scores for two major airlines in Malaysia. Design/methodology/approach A Sentiment Intensity Calculator (SentI-Cal) was developed by assigning individual weights to each letter repetition, and tested it using data collected from official Facebook pages of the airlines. Findings Evaluation metrics indicate that SentI-Cal outperforms the baseline tool Semantic Orientation Calculator (SO-CAL), with an accuracy of 90.7 percent compared to 58.33 percent for SO-CAL. Practical implications A more accurate sentiment score allows airline services to easily obtain a better understanding of the sentiments of their customers, hence providing opportunities in improving their airline services. Originality/value Proposed mechanism calculates sentiment intensity of social media text by assigning individual weightage to each repeated letter and exclamation mark thus producing a more accurate sentiment score.

Artificial Intelligence, Social Media and Depression. ‘Patient’ Autonomy Revisited

2021 ◽  
Vol 66 (Special Issue) ◽  
pp. 133-133
Author(s):  
Regina Mueller ◽  
◽  
Sebastian Laacke ◽  
Georg Schomerus ◽  
Sabine Salloch ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Social Media ◽  
Mental Disorders ◽  
Patient Autonomy ◽  
Ethical Challenges ◽  
Traditional Concept ◽  
Ethical Implications ◽  
Health Related ◽  
Twitter Users ◽  
Using Data

"Artificial Intelligence (AI) systems are increasingly being developed and various applications are already used in medical practice. This development promises improvements in prediction, diagnostics and treatment decisions. As one example, in the field of psychiatry, AI systems can already successfully detect markers of mental disorders such as depression. By using data from social media (e.g. Instagram or Twitter), users who are at risk of mental disorders can be identified. This potential of AI-based depression detectors (AIDD) opens chances, such as quick and inexpensive diagnoses, but also leads to ethical challenges especially regarding users’ autonomy. The focus of the presentation is on autonomy-related ethical implications of AI systems using social media data to identify users with a high risk of suffering from depression. First, technical examples and potential usage scenarios of AIDD are introduced. Second, it is demonstrated that the traditional concept of patient autonomy according to Beauchamp and Childress does not fully account for the ethical implications associated with AIDD. Third, an extended concept of “Health-Related Digital Autonomy” (HRDA) is presented. Conceptual aspects and normative criteria of HRDA are discussed. As a result, HRDA covers the elusive area between social media users and patients. "

Robust Finger Vein Recognition Based on Deep CNN with Spatial Attention and Bias Field Correction

2021 ◽  
Vol 30 (01) ◽  
pp. 2140005
Author(s):  
Zhe Huang ◽  
Chengan Guo
Keyword(s):  
Spatial Attention ◽  
Transfer Learning ◽  
Learning Strategy ◽  
Bias Field ◽  
The Public ◽  
Finger Vein ◽  
Bias Field Correction ◽  
Training Samples ◽  
Vein Recognition ◽  
Finger Vein Recognition

As one of the biometric information based authentication technologies, finger vein recognition has received increasing attention due to its safety and convenience. However, it is still a challenging task to design an efficient and robust finger vein recognition system because of the low quality of the finger vein images, lack of sufficient number of training samples with image-level annotated information and no pixel-level finger vein texture labels in the public available finger vein databases. In this paper, we propose a novel CNN-based finger vein recognition approach with bias field correction, spatial attention mechanism and a multistage transfer learning strategy to cope with the difficulties mentioned above. In the proposed method, the bias field correction module is to remove the unbalanced bias field of the original images by using a two-dimensional polynomial fitting algorithm, the spatial attention module is to enhance the informative vein texture regions while suppressing the other less informative regions, and the multistage transfer learning strategy is to solve the problem caused by insufficient training for CNN-based model due to lack of labeled training samples in the public finger vein databases. Moreover, several measures, including a label smoothing scheme and data augmentation, are exploited to improve the performance of the proposed method. Extensive experiments have been conducted in the work on three public databases, and the results show that the proposed approach outperforms the existing state-of-the-art methods.

scholarly journals The Influence of Heuristic judgments in Social Media on Corporate Reputation: A Study in Spanish Leader Companies

2020 ◽  
Vol 12 (4) ◽  
pp. 1640 ◽  
Author(s):  
Luis Manuel Cerdá Suárez ◽  
Jesús Perán López ◽  
Belén Cambronero Saiz
Keyword(s):  
Social Media ◽  
Corporate Reputation ◽  
Cognitive Biases ◽  
Managerial Performance ◽  
Economic Agents ◽  
Using Data ◽  
Business And Management ◽  
Positive Effect ◽  
Different Levels ◽  
High Uncertainty

From a corporate-side perspective, the communication of reputational actions and news of companies becomes critical for success. However, in communication, business, and management studies, heuristics can be understood as simple cognitive processes that allow assessments, predictions, and decisions to be made quickly and efficiently by consumers and economic agents. This aspect can sometimes lead to cognitive biases, especially when little information is available or in situations of high uncertainty. The aim of this research is to investigate the influence of heuristic judgments in social media on corporate reputation ratings obtained in Spanish leader companies. Using data collected in Spain, this paper analyzes the influence of heuristics concerning news items on corporate reputation, measured by the Monitor Empresarial de Reputación Corporativa (MERCO) Index. The main finding of this paper is that the total number of news items has a positive effect on corporate reputation, particularly in the categories of culture-values, results/image, expansion, and sponsorship/donations. Additionally, this work serves as a repository of knowledge applicable to similar situations considering the specificities of each particular case. The importance to intervene on certain variables at different levels of managerial performance is described and implications for companies are discussed in these pages.

Sign in / Sign up

Export Citation Format

Share Document