scholarly journals DeepVisInterests : Deep data analysis for topics of interests prediction

2021 ◽  
Author(s):  
Onsa Lazzez ◽  
Adel Alimi ◽  
Wael Ouarda
Keyword(s):  
Data Analysis ◽  
Semantic Representation ◽  
Experimental Studies ◽  
Research Area ◽  
Visual Data ◽  
Analysis Techniques ◽  
Database Evaluation ◽  
Extraction Step ◽  
Textual Data ◽  
Important Research Area

Deep data analysis for latent information prediction has been an important research area. Many of the existing solutions have used the textual data and have obtained an accurate results for predicting users' interests and other latent attributes. However, little attention has been paid to visual data that is becoming increasingly popular in recent times. In this paper, we addresses the problem of discovering the attributed interest and of analyzing the performance of the automatic prediction using a comparison with the self assessed topics of interest (topics of interest provided by the user in a proposed questionnaire) based on data analysis techniques applied on the users visual data. We analyze the content of each user's images to aggregate the image-level users' interests distribution in order to obtain the user-level users' interest distribution. To do this, we employ the pretrained ImageNet convolutional neural networks architectures for the feature extraction step and to construct the ontology, as the users' interests model, in order to learn the semantic representation for the popular topics of interests defined by social networks (e.g., Facebook). Our experimental studies show that this analysis, on the most relevant features, enhances the performance of the prediction framework. In order to improve our framework's robustness and generalization with unknown users' profiles, we propose a novel database evaluation. Our proposed framework provided promising results which are competitive to state-of-the-art techniques with an accuracy of 0.80.

scholarly journals DeepVisInterests : Deep data analysis for topics of interests prediction

2021 ◽  
Author(s):  
Onsa Lazzez ◽  
Adel Alimi ◽  
Wael Ouarda
Keyword(s):  
Data Analysis ◽  
Semantic Representation ◽  
Experimental Studies ◽  
Research Area ◽  
Visual Data ◽  
Analysis Techniques ◽  
Database Evaluation ◽  
Extraction Step ◽  
Textual Data ◽  
Important Research Area

Deep data analysis for latent information prediction has been an important research area. Many of the existing solutions have used the textual data and have obtained an accurate results for predicting users' interests and other latent attributes. However, little attention has been paid to visual data that is becoming increasingly popular in recent times. In this paper, we addresses the problem of discovering the attributed interest and of analyzing the performance of the automatic prediction using a comparison with the self assessed topics of interest (topics of interest provided by the user in a proposed questionnaire) based on data analysis techniques applied on the users visual data. We analyze the content of each user's images to aggregate the image-level users' interests distribution in order to obtain the user-level users' interest distribution. To do this, we employ the pretrained ImageNet convolutional neural networks architectures for the feature extraction step and to construct the ontology, as the users' interests model, in order to learn the semantic representation for the popular topics of interests defined by social networks (e.g., Facebook). Our experimental studies show that this analysis, on the most relevant features, enhances the performance of the prediction framework. In order to improve our framework's robustness and generalization with unknown users' profiles, we propose a novel database evaluation. Our proposed framework provided promising results which are competitive to state-of-the-art techniques with an accuracy of 0.80.

scholarly journals Formalization and Knowledge Representation in Advanced Engineering Informatics

2022 ◽  
pp. 8-14
Author(s):  
Mohammad Biglarbegian
Keyword(s):  
Data Analysis ◽  
Knowledge Representation ◽  
Conceptual Framework ◽  
Conceptual Model ◽  
Research Area ◽  
Bottom Up ◽  
Engineering Knowledge ◽  
Analysis Techniques ◽  
Scientific Approach ◽  
Social Scientific

The primary goal of this article in the research area of Advanced Engineering Informatics (AEIs) is to depict and formalize engineering knowledge that is multidimensional. This paper introduces conceptual framework and rationality as implicit methodologies to regularize knowledge. The objective of professionals, as well as the circumstances in which they work, should be considered when depicting and standardizing knowledge. The constructs of epistemology, rationality, and context are used to communicate various alternative data analysis techniques and practices that expert can use to institutionalize intricate engineering expertise and to substantiate whether a specialized conceptual model can support engineers with their challenging operations. A bottom-up method of research in advanced engineering, encompassing engineers, is suggested in this article. A social scientific approach to engendering knowledge for formalization and validating it is also recommended by us for scientists.

Sentiment Classification-How to Quantify Public Emotions Using Twitter

2018 ◽  
Vol 10 (1) ◽  
pp. 57-71 ◽  
Author(s):  
Prerna Mahajan ◽  
Anamika Rana
Keyword(s):  
Sentiment Analysis ◽  
Social Networking Sites ◽  
Research Area ◽  
Sentiment Classification ◽  
Government Policies ◽  
Emotion Detection ◽  
Textual Data ◽  
Good Classification ◽  
Important Research Area ◽  
Sentiment Score

This article describes how with the tremendous popularity in the usage of social media has led to the explosive growth in unstructured data available on various social networking sites. Sentiment analysis of textual data collected from such platforms has become an important research area. In this article, the sentiment classification approach which employs an emotion detection technique is presented. To identify the emotions this paper uses the NRC lexicon based approach for identifying polarity of emotions. A score is computed to quantify emotions obtained from NRC lexicon approach. The method proposed has been tested on twitter datasets of government policies and reforms, more about current NDA government initiatives in India. The polarity components apply and classify the tweets into eight predefined emotions. This article performs both quantitative and sentiment analysis processes with the objective of analyzing the opinion conveyed to each social content, assign a category (+ve, -ve & neutral) or numbered sentiment score. The assigned scores have been classified using six different machine classification algorithms. Good classification results are achieved with the data.

PENGARUH PERBAIKAN BERKESINAMBUNGAN TERHADAP KINERJA KARYAWAN (STUDI KASUS DI PT.RENTANG BUANA NIAGAMAKMUR TASIKMALAYA)

2019 ◽  
Vol 3 (1) ◽  
pp. 31-41
Author(s):  
Sri Sudiarti
Keyword(s):  
Data Analysis ◽  
Continuous Improvement ◽  
Research Method ◽  
Employee Performance ◽  
Sampling Technique ◽  
Positive Influence ◽  
Performance Criteria ◽  
Coefficient Of Determination ◽  
Analysis Techniques ◽  
Simple Regression

The objectives of this research are to know and to analyze about the effect of Continuous Improvement on the performance of employees at PT. Rentang Buana Niagamakmur (PT.RBN) Tasikmalaya. Research method which applied in this research is survey research method, while data collecting technique is done by through questionaire. Sampling technique applies sample is accidental sampling technique and the size sample is 55 respondents. Data analysis techniques used in the study is simple regression technique, analysis of the coefficient of determination  and t test. The results showed that the Continuous Improvement  including both criteria, including employee performance criteria, as well as Continuous Improvement  has a positive influence on employee performance of 76,4% in PT . Rentang Buana Niagamakmur (PT.RBN) Tasikmalaya.

INDONESIA LANGUAGE INTERFERENCE FORM IN BASIC PPL LEARNING THAILAND UNHASY COLLEGE SYUDENTS

2020 ◽  
Vol 8 (2) ◽  
pp. 38
Author(s):  
Siti Mariana Ulfa
Keyword(s):  
Qualitative Research ◽  
Data Analysis ◽  
Data Collection ◽  
Teaching Practice ◽  
Data Presentation ◽  
Analysis Techniques ◽  
Thai Students ◽  
The Impact ◽  
Collection Methods ◽  
Recording Techniques

AbstractHumans on earth need social interaction with others. Humans can use more than one language in communication. Thus, the impact that arises when the use of one or more languages is the contact between languages. One obvious form of contact between languages is interference. Interference can occur at all levels of life. As in this study, namely Indonesian Language Interference in Learning PPL Basic Thailand Unhasy Students. This study contains the form of interference that occurs in Thai students who are conducting teaching practices in the classroom. This type of research is descriptive qualitative research that seeks to describe any interference that occurs in the speech of Thai students when teaching practice. Data collection methods in this study are (1) observation techniques, (2) audio-visual recording techniques using CCTV and (3) recording techniques, by recording all data that has been obtained. Whereas the data wetness uses, (1) data triangulation, (2) improvement in perseverance and (3) peer review through discussion. Data analysis techniques in this study are (1) data collection, (2) data reduction, (3) data presentation and (4) conclusions. It can be seen that the interference that occurs includes (1) interference in phonological systems, (2) interference in morphological systems and (3) interference in syntactic systems. 

PENGARUH KEPEMIMPINAN DAN MOTVASI KERJA TERHADAP KUALITAS PELAYANAN PUBLIK (STUDI KASUS PADA KANTOR KEMENTERIAN AGAMA SUNGAI PENUH )

2020 ◽  
Author(s):  
Pahrizal
Keyword(s):  
Data Analysis ◽  
Service Quality ◽  
Public Service ◽  
Random Sampling ◽  
Secondary Data ◽  
Sampling Technique ◽  
Simple Random Sampling ◽  
Primary Data ◽  
Analysis Techniques ◽  
Intervening Variables

The research is proposed to test the influence of Leadership and Motivation Work on Public Service Quality. The population in this study was the Kantor Kementerian Agama Sungai Penuh who had received the last 1 year service at the Kantor Kementerian Agama Sungai Penuh, amounting to 260 people. Furthermore, by using the Slovin formula, a sample size of 158 people was chosen with a sampling technique based on Simple Random Sampling. This study uses primary data and secondary data. Data analysis techniques used are path analysis and hypothesis testing using t test with data analysis using SPSS version 20. The results of the study based on showing that partially the Leadership and motivation work have a positive and significant effect on Public Service Quality. The results also show that motivation work variables act as intervening variables between Leadership and Public Service Quality.

Ricerca preliminare sulla valutazione Italiana dell'Internet Disorder Scale – Short Form (IDS9-SF)

2019 ◽  
Author(s):  
Paolo Soraci
Keyword(s):  
Social Networks ◽  
Factor Analysis ◽  
Data Analysis ◽  
Concurrent Validity ◽  
Short Form ◽  
Analysis Techniques ◽  
Validity Criterion ◽  
Preliminary Research ◽  
Nomological Validity ◽  
Italian Territory

The purpose of this study is to create a new tool capable of diagnosing the severity of internet addiction (IA) and is based on the nine IGD criteria. These same criteria were suggested by the APA in the last edition of the DSM-51. A sample was recruited with a method of convenience and 300+ participants were recruited through different forums and social networks. The construct validity of the IDS9SF test was achieved through factor analysis and nomological validity. The concurrent validity, criterion and reliability of the test itself have been thoroughly investigated through the most common and consolidated data analysis techniques, confirming that the same test has sufficient psychometric properties to be used also in the Italian territory. Furthermore it is necessary to remember that this preliminary research is only valid in the field of data and statistics with all the limitations of the case and cannot be used for a real clinical evaluation.

Pengaruh Program E-Samsat terhadap Kepatuhan Wajib Pajak Kendaraan Bermotor Dengan Kepuasan Kualitas Pelayanan Sebagai Variabel Intervening (Studi Kasus Samsat Daerah Istimewa Yogyakarta)

2020 ◽  
Vol 15 (2) ◽  
Author(s):  
Dewi Kusuma Wardani
Keyword(s):  
Data Analysis ◽  
Service Quality ◽  
Path Analysis ◽  
Sampling Method ◽  
Motor Vehicle ◽  
Primary Data ◽  
Significant Positive Effect ◽  
Analysis Techniques ◽  
Positive Effect ◽  
Special Region

The purpose of this research is to know, the influence of e-samsat program to the satisfaction of service quality, the influence of the satisfaction of service quality to the compliance of motor vehicle taxpayer, the influence of e-samsat program to the compliance of the motor vehicle taxpayers, and to know the effect of e-samsat program on compulsory compliance motor vehicle tax through satisfaction of service quality as intervening variable in Special Region of Yogyakarta. We use primary data. The sample of research is 75 taxpayers but the sample that can be processed only 74.The sampling method used is purposive sampling. Data analysis techniques used path analysis, t test, F test, and R2 test. Based on result of research by using path analysis that, e-samsat program have a significant positive effect to service quality satisfaction, service quality satisfaction has a significant positive effect to vehicle taxpayer compliance, e-samsat program has a significant positive effect on vehicle taxpayer compliance and program e-samsat has a significant positive effect on the compliance of motor vehicle taxpayers through the satisfaction of service quality.Keywords: e-samsat program, service quality satisfaction, and taxpayer compliance

Perkembangan Bahasa Anak Usia 12 Hingga 24 Bulan di Semarang

2018 ◽  
Vol 1 (2) ◽  
pp. 66
Author(s):  
Marini Marini ◽  
Khasanah Khasanah
Keyword(s):  
Data Analysis ◽  
Data Collection ◽  
Model Checking ◽  
Language Development ◽  
Qualitative Method ◽  
Questionnaire Data ◽  
Daily Lives ◽  
Analysis Techniques ◽  
Development Of Language

Abstract The  problem  of this research is : How is the language development of children age 12 to 24 months in Semarang ?. The purpose of this study is to describe widely and deeply about language development the children age 12 to 24 in Semarang. The method used in this research is qualitative method. Data collection is done by observation, interviews, and questionnaire. Data analysis techniques using Miles Hubermen’s model. Checking the validity of the data using triangulation data. The results showed that the development of language of children aged 12 to 24 months in Semarang in expressive is: can produce sound almost perfect in several words; Some of the letters of the words missing from the pronunciation; The missing letters are usually consonants; Haven't been able to pronounce the letter s and r; In General, most people are able to understand the speech of the children is an adult who is close to the child; There is a word that can be spelled perfectly by the child. The words are by and large is the words that are simple and close to the children's daily lives. As for the generally receptive: children can follow and obey what is spoken by adults; The children seem to understand when the adults were talking about them; and children  can understand  to the words that they  heard more than that they can speak.   Keywords: Language, children, expressive, receptive, word.    

Sign in / Sign up

Export Citation Format

Share Document