scholarly journals Exploring Impact of Age and Gender on Sentiment Analysis Using Machine Learning

Electronics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 374 ◽  
Author(s):  
Sudhanshu Kumar ◽  
Monika Gahalawat ◽  
Partha Pratim Roy ◽  
Debi Prosad Dogra ◽  
Byung-Gyu Kim
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Age Groups ◽  
Modern World ◽  
Support Vector ◽  
Digital Information ◽  
Age And Gender ◽  
And Gender ◽  
The Impact

Sentiment analysis is a rapidly growing field of research due to the explosive growth in digital information. In the modern world of artificial intelligence, sentiment analysis is one of the essential tools to extract emotion information from massive data. Sentiment analysis is applied to a variety of user data from customer reviews to social network posts. To the best of our knowledge, there is less work on sentiment analysis based on the categorization of users by demographics. Demographics play an important role in deciding the marketing strategies for different products. In this study, we explore the impact of age and gender in sentiment analysis, as this can help e-commerce retailers to market their products based on specific demographics. The dataset is created by collecting reviews on books from Facebook users by asking them to answer a questionnaire containing questions about their preferences in books, along with their age groups and gender information. Next, the paper analyzes the segmented data for sentiments based on each age group and gender. Finally, sentiment analysis is done using different Machine Learning (ML) approaches including maximum entropy, support vector machine, convolutional neural network, and long short term memory to study the impact of age and gender on user reviews. Experiments have been conducted to identify new insights into the effect of age and gender for sentiment analysis.

scholarly journals Financial Context News Sentiment Analysis for the Lithuanian Language

2021 ◽  
Vol 11 (10) ◽  
pp. 4443
Author(s):  
Rokas Štrimaitis ◽  
Pavel Stefanovič ◽  
Simona Ramanauskaitė ◽  
Asta Slotkienė
Keyword(s):  
Machine Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Experimental Investigations ◽  
Support Vector ◽  
Applied Machine Learning ◽  
Bayes Algorithm ◽  
Website Content

Financial area analysis is not limited to enterprise performance analysis. It is worth analyzing as wide an area as possible to obtain the full impression of a specific enterprise. News website content is a datum source that expresses the public’s opinion on enterprise operations, status, etc. Therefore, it is worth analyzing the news portal article text. Sentiment analysis in English texts and financial area texts exist, and are accurate, the complexity of Lithuanian language is mostly concentrated on sentiment analysis of comment texts, and does not provide high accuracy. Therefore in this paper, the supervised machine learning model was implemented to assign sentiment analysis on financial context news, gathered from Lithuanian language websites. The analysis was made using three commonly used classification algorithms in the field of sentiment analysis. The hyperparameters optimization using the grid search was performed to discover the best parameters of each classifier. All experimental investigations were made using the newly collected datasets from four Lithuanian news websites. The results of the applied machine learning algorithms show that the highest accuracy is obtained using a non-balanced dataset, via the multinomial Naive Bayes algorithm (71.1%). The other algorithm accuracies were slightly lower: a long short-term memory (71%), and a support vector machine (70.4%).

Attachment points, team identification and sponsorship outcomes: evidence from the Indian Premier League

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Giridhar B. Kamath ◽  
Shirshendu Ganguli ◽  
Simon George
Keyword(s):  
Structural Equation ◽  
Group Analysis ◽  
Age Groups ◽  
Team Identification ◽  
Age And Gender ◽  
Content Type ◽  
Behavioural Intentions ◽  
Premier League ◽  
And Gender ◽  
The Impact

PurposeThis paper tests and validates a conceptual model linking the attachment points, team identification, attitude towards the team sponsors and the behavioural intentions in the context of Indian Premier League (IPL), while testing for the moderating effects of age and gender.Design/methodology/approachData were collected from 1,053 participants through both online and offline survey and then analyzed using exploratory factor analysis (EFA) and structural equation modelling (SEM).FindingsAttachment points influence the formation of team identification, which, in turn, affect the attitude towards the team sponsors. Attitude towards the team sponsors influence the behavioural intentions. Player attachment influences team identification the most. Age and gender have a moderating effect on the constructs of the study. Team identification in females is stronger because of attachment to sports, whereas males have stronger team identification based on player attachment. Males have a stronger intention to spread positive word of mouth (WOM) about sponsor products as compared to the female respondents. The younger age group of less than 21 years has more intention to spread positive WOM compared to the other age groups considered in the study.Practical implicationsThis study contributes towards sports sponsorship research and the paradigms of social identity and attachment theories. Moreover, it will also help the marketers (sponsors) in IPL to strategically market their brands.Originality/valueThis is the first study to investigate the impact of attachment points on sponsorship outcomes in the context of IPL. Further, it is also the first to investigate the purchase intentions and WOM for the team sponsors in IPL. The multi-group analysis results will provide insights into marketers to better understand IPL viewers' segments and their behaviour.

scholarly journals Sentiment Analysis of Lithuanian Texts Using Traditional and Deep Learning Approaches

Computers ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 4 ◽  
Author(s):  
Jurgita Kapočiūtė-Dzikienė ◽  
Robertas Damaševičius ◽  
Marcin Woźniak
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Approaches ◽  
Full Dataset ◽  
Learning Techniques ◽  
Long Short Term Memory

We describe the sentiment analysis experiments that were performed on the Lithuanian Internet comment dataset using traditional machine learning (Naïve Bayes Multinomial—NBM and Support Vector Machine—SVM) and deep learning (Long Short-Term Memory—LSTM and Convolutional Neural Network—CNN) approaches. The traditional machine learning techniques were used with the features based on the lexical, morphological, and character information. The deep learning approaches were applied on the top of two types of word embeddings (Vord2Vec continuous bag-of-words with negative sampling and FastText). Both traditional and deep learning approaches had to solve the positive/negative/neutral sentiment classification task on the balanced and full dataset versions. The best deep learning results (reaching 0.706 of accuracy) were achieved on the full dataset with CNN applied on top of the FastText embeddings, replaced emoticons, and eliminated diacritics. The traditional machine learning approaches demonstrated the best performance (0.735 of accuracy) on the full dataset with the NBM method, replaced emoticons, restored diacritics, and lemma unigrams as features. Although traditional machine learning approaches were superior when compared to the deep learning methods; deep learning demonstrated good results when applied on the small datasets.

The Swedish Version of the Temperament and Character Inventory (TCI)

2008 ◽  
Vol 24 (1) ◽  
pp. 14-21 ◽  
Author(s):  
Sven Brändström ◽  
Sören Sigvardsson ◽  
Per-Olof Nylander ◽  
Jörg Richter
Keyword(s):  
Personality Assessment ◽  
Age Groups ◽  
Temperament And Character Inventory ◽  
Swedish Version ◽  
Age And Gender ◽  
Younger Age ◽  
Character Inventory ◽  
And Gender ◽  
Independent Effects ◽  
The Impact

Abstract. In order to establish new norms of the Swedish version of the Temperament and Character Inventory (TCI), data from 2,209 Swedish individuals (age between 13 and 80) was analyzed. The second aim was to evaluate the impact of age and gender on the questionnaire scores. The third aim was to investigate whether the TCI can be meaningfully applied to adolescents in personality assessment as a basis for further research and clinical studies. Age and gender showed independent effects on personality dimensions, which implies that age and gender specific norms have to be established for the TCI. Furthermore, the results in terms of inconsistencies in the correlational and factorial structure, as well as low internal consistency scores in the younger age groups, suggest that the adult version of the TCI should not be applied below the age of 17; for these age groups we recommend the use of the junior TCI (JTCI). The inventory is under further development and several items are in need of revision in order to create less complicated formulations, enabling an improvement in the psychometrics.

Two-Level Classification in Determining the Age and Gender Group of a Speaker

2021 ◽  
Vol 18 (5) ◽  
Author(s):  
Ergün Yücesoy
Keyword(s):  
Classification Accuracy ◽  
Age Groups ◽  
Gaussian Mixture ◽  
Support Vector ◽  
Optimum Number ◽  
Mel Frequency Cepstral Coefficients ◽  
Age And Gender ◽  
Number Of Components ◽  
And Gender

In this study, the classification of the speakers according to age and gender was discussed. Age and gender classes were first examined separately, and then by combining these classes a classification with a total of 7 classes was made. Speech signals represented by Mel-Frequency Cepstral Coefficients (MFCC) and delta parameters were converted into Gaussian Mixture Model (GMM) mean supervectors and classified with a Support Vector Machine (SVM). While the GMM mean supervectors were formed according to the Maximum-a-posteriori (MAP) adaptive GMM-Universal Background Model (UBM) configuration, the number of components was changed from 16 to 512, and the optimum number of components was decided. Gender classification accuracy of the system developed using aGender dataset was measured as 99.02% for two classes and 92.58% for three classes and age group classification accuracy was measured as 67.03% for female and 63.79% for male. In the classification of age and gender classes together in one step, an accuracy of 61.46% was obtained. In the study, a two-level approach was proposed for classifying age and gender classes together. According to this approach, the speakers were first divided into three classes as child, male and female, then males and females were classified according to their age groups and thus a 7-class classification was realized. This two-level approach was increased the accuracy of the classification in all other cases except when 32-component GMMs were used. While the highest improvement of 2.45% was achieved with 64 component GMMs, an improvement of 0.79 was achieved with 256 component GMMs.

scholarly journals Age and Gender Impact on Password Hygiene

2022 ◽  
Vol 12 (2) ◽  
pp. 894
Author(s):  
Aušrius Juozapavičius ◽  
Agnė Brilingaitė ◽  
Linas Bukauskas ◽  
Ricardo Gregorio Lugo
Keyword(s):  
Age Groups ◽  
Age And Gender ◽  
User Groups ◽  
Measured Effect ◽  
Active Research ◽  
And Gender ◽  
The Impact ◽  
Password Strength ◽  
Security Incidents ◽  
Simple Sequence

Password hygiene plays an essential part in securing systems protected with single-factor authentication. A significant fraction of security incidents happen due to weak or reused passwords. The reasons behind differences in security vulnerable behaviour between various user groups remains an active research topic. The paper aims to identify the impact of age and gender on password strength using a large password dataset. We recovered previously hashed passwords of 102,120 users from a leaked customer database of a car-sharing company. Although the measured effect size was small, males significantly had stronger passwords than females for all age groups. Males aged 26–45 were also significantly different from all other groups, and password complexity decreased with age for both genders equally. Overall, very weak password hygiene was observed, 72% of users based their password on a word or used a simple sequence of digits, and passwords of over 39% of users were found in word lists of previous leaks.

The Influence of Gender and Menopausal Status on Hba1c Variation in a Big Data Study of a Saudi Population

2020 ◽  
Vol 16 ◽  
Author(s):  
Abdullah S. Alghamdi ◽  
Abdulaziz Alqadi ◽  
Richard O. Jenkins ◽  
Parvez I. Haris
Keyword(s):  
Diabetes Mellitus ◽  
Menopausal Status ◽  
Age Groups ◽  
Glycated Haemoglobin ◽  
Adult Women ◽  
Linear Regression Models ◽  
Age And Gender ◽  
And Gender ◽  
The Impact ◽  
Hba1c Levels

Background: Glycated haemoglobin (HbA1c) is the gold standard measurement in the screening, diagnosis and monitoring of diabetes mellitus. Saudi Arabia has a high prevalence of diabetes mellitus that is expected to rise, and the HbA1c test is commonly used in the screening, diagnosis and monitoring of diabetes. Objective: his study aims to assess the impact of age and gender on HbA1c levels, and the influence of menopausal status on HbA1c variation in a large group of Saudis. Method: Age, gender, and HbA1c results of 168,614 Saudi adult individuals were obtained from their medical records. Patients’ records were extracted irrespective of their status regarding presence of diabetes and status of glycaemic control. Linear regression models were used for predicting HbA1c from age and gender, and their interaction term. HbA1c levels were compared between genders in different age groups and different HbA1c categories. Results and Discussion: There was a statistically significant positive correlation between age and HbA1c levels, where for each ten years increase in age HbA1c increased by 0.35%. Although the overall mean HbA1c in women was significantly lower than in men (P < 0.001), women show a significant increase in HbA1c with increased age compared to men (B = 0.014, P < 0.001). Furthermore, the mean HbA1c levels in age group > 50 years was significantly higher than before that age (P < 0.001). Thus, HbA1c increased by 1.118% in age > 50 years group compared to age ≤ 50 years, and this increase in HbA1c was significantly higher in women compared to men (B = 0.495, P < 0.001). Conclusion: HbA1c levels are lower in women before the estimated menopausal age, which should be taken into consideration when using HbA1c for screening, diagnosis, and monitoring of diabetes in Saudi adult women. The short lifespan of red blood cells, due to loss of blood through menstruation, in women before menopause age, is a possible reason for these variations.

Hand Force of Men and Women Over 65 Years of Age as Measured by Maximum Pinch and Grip Force

2008 ◽  
Vol 16 (1) ◽  
pp. 24-41 ◽  
Author(s):  
Caroline W. Stegink Jansen ◽  
Bruce R. Niebuhr ◽  
Daniel J. Coussirat ◽  
Dana Hawthorne ◽  
Laura Moreno ◽  
...  
Keyword(s):  
Grip Force ◽  
Force Measurement ◽  
Age Groups ◽  
Normative Values ◽  
Cross Sectional ◽  
Age And Gender ◽  
Pinch Force ◽  
Hand Force ◽  
And Gender ◽  
The Impact

This cross-sectional study aimed to assess the impact of age and gender on 4 measures of grip and pinch force of well elderly community dwellers and to provide normative values. The hypotheses were that age and gender affect pinch and grip force and that these 2 factors might interact. Hand strength of 224 seniors 65–92 years old was tested. Grip and pinch force decreased in successively older age groups past 65 years. Men’s grip force exceeded that of women in all age groups. Men’s hand-force decline was steeper than that of women over successive age groups, suggesting that gender differences in force decreased with age. Trends were the same for all 4 types of grip- and pinch-force measurement but were most clearly visible in grip and key-pinch force. Norms were provided for seniors age 65–85+ years in 5-yr increments.

Touch-Based Active Cloud Authentication Using Traditional Machine Learning and LSTM on a Distributed Tensorflow Framework

2019 ◽  
Vol 18 (04) ◽  
pp. 1950022
Author(s):  
Dylan J. Gunn ◽  
Zhipeng Liu ◽  
Rushit Dave ◽  
Xiaohong Yuan ◽  
Kaushik Roy
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Mobile Device ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Modern World ◽  
Support Vector ◽  
Learning Classifier ◽  
Cloud Framework ◽  
Computationally Intensive

In this modern world, mobile devices have been paired with the cloud environment to scale the voluminous amount of generated data. The implementation comes at the cost of privacy as proprietary data can be stolen in transit to the cloud, or victims’ phones can be seized along with synced data from cloud. The attacker can gain access to the phone through shoulder surfing, or even spoofing attacks. Our approach is to mitigate this issue by proposing an active cloud authentication framework using touch biometric pattern. To the best of our knowledge, active cloud authentication using touch dynamics for mobile cloud computing has not been explored in the literature. This research creates a proof of concept that will lead into a simulated cloud framework for active authentication. Given the amount of data captured by the mobile device from user activity, it can be a computationally intensive process for the mobile device to handle with such limited resources. To solve this, we simulated a post-transmission process of data to the cloud so that we could implement the authentication process within the cloud. We evaluated the touch data using traditional machine learning algorithms, such as Random Forest (RF), Support Vector Machine (SVM), and also using a deep learning classifier, the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) algorithms. The novelty of this work is two-fold. First, we develop a distributed tensorflow framework for cloud authentication using touch biometric pattern. This framework helps alleviate the drawback of the computationally intensive recognition of the substantial amount of raw data from the user. Second, we apply the RF, SVM, and a deep learning classifier, the LSTM-RNN, on the touch data to evaluate the performance of the proposed authentication scheme. The proposed approach shows a promising performance with an accuracy of 99.0361% using RF on the distributed tensorflow framework.

The impact of generation on the risk of road accidents

2019 ◽  
Vol 64 (2) ◽  
pp. 64-82
Author(s):  
Beata Jackowska ◽  
Ewa Wycinka
Keyword(s):  
Age Groups ◽  
Analysis Data ◽  
Road Accident ◽  
Research Centre ◽  
Road Accidents ◽  
Age And Gender ◽  
The Road ◽  
And Gender ◽  
Gender Groups ◽  
The Impact

The paper deals with the widespread perception, popular since 2017, that millennials are the worst drivers. In motor insurance, it is commonly known that age and gender are significant determinants of accidents’ risk. Nowadays, millennials are the youngest drivers. Thus, the question arises whether, apart from the age, generation isa risk factor. The aim of this paper is to verify whether generation influences the level of the road accidents rate in Poland besides age and gender of drivers. Due to the downward trend of this rate, the relative risk of road accidents was analysed among licensed drivers in Poland in the years 2006—2017. For the analysis data of the Polish National Police, Polish Road Safety Observatory, Statistics Poland, Social Diagnosis as well as Public Opinion Research Centre were used. The percentage of licensed drivers was estimated for age and gender groups as well as the percentage of millennials in these groups, according to the generation theory. The results of the empirical study for age groups of both perpetrators of the accidents and drivers involved in accidents do not confirm the hypothesis about the impact of the generation on the risk of a road accident.

Sign in / Sign up

Export Citation Format

Share Document