scholarly journals Supervised learning and resampling techniques on DISC personality classification using Twitter information in Bahasa Indonesia

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ema Utami ◽  
Irwan Oyong ◽  
Suwanto Raharjo ◽  
Anggit Dwi Hartanto ◽  
Sumarni Adi
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Language Processing ◽  
Design Methodology ◽  
Sampling Technique ◽  
Profile Data ◽  
Content Type ◽  
Robust Model ◽  
Personality Classification ◽  
Bahasa Indonesia

PurposeGathering knowledge regarding personality traits has long been the interest of academics and researchers in the fields of psychology and in computer science. Analyzing profile data from personal social media accounts reduces data collection time, as this method does not require users to fill any questionnaires. A pure natural language processing (NLP) approach can give decent results, and its reliability can be improved by combining it with machine learning (as shown by previous studies).Design/methodology/approachIn this, cleaning the dataset and extracting relevant potential features “as assessed by psychological experts” are essential, as Indonesians tend to mix formal words, non-formal words, slang and abbreviations when writing social media posts. For this article, raw data were derived from a predefined dominance, influence, stability and conscientious (DISC) quiz website, returning 316,967 tweets from 1,244 Twitter accounts “filtered to include only personal and Indonesian-language accounts”. Using a combination of NLP techniques and machine learning, the authors aim to develop a better approach and more robust model, especially for the Indonesian language.FindingsThe authors find that employing a SMOTETomek re-sampling technique and hyperparameter tuning boosts the model’s performance on formalized datasets by 57% (as measured through the F1-score).Originality/valueThe process of cleaning dataset and extracting relevant potential features assessed by psychological experts from it are essential because Indonesian people tend to mix formal words, non-formal words, slang words and abbreviations when writing tweets. Organic data derived from a predefined DISC quiz website resulting 1244 records of Twitter accounts and 316.967 tweets.

scholarly journals Applying natural language processing and machine learning techniques to patient experience feedback: a systematic review

2021 ◽  
Vol 28 (1) ◽  
pp. e100262
Author(s):  
Mustafa Khanbhai ◽  
Patrick Anyadi ◽  
Joshua Symons ◽  
Kelsey Flott ◽  
Ara Darzi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Social Media ◽  
Natural Language Processing ◽  
Natural Language ◽  
Patient Experience ◽  
Language Processing ◽  
Performance Metrics ◽  
Free Text ◽  
Patient Feedback

ObjectivesUnstructured free-text patient feedback contains rich information, and analysing these data manually would require a lot of personnel resources which are not available in most healthcare organisations.To undertake a systematic review of the literature on the use of natural language processing (NLP) and machine learning (ML) to process and analyse free-text patient experience data.MethodsDatabases were systematically searched to identify articles published between January 2000 and December 2019 examining NLP to analyse free-text patient feedback. Due to the heterogeneous nature of the studies, a narrative synthesis was deemed most appropriate. Data related to the study purpose, corpus, methodology, performance metrics and indicators of quality were recorded.ResultsNineteen articles were included. The majority (80%) of studies applied language analysis techniques on patient feedback from social media sites (unsolicited) followed by structured surveys (solicited). Supervised learning was frequently used (n=9), followed by unsupervised (n=6) and semisupervised (n=3). Comments extracted from social media were analysed using an unsupervised approach, and free-text comments held within structured surveys were analysed using a supervised approach. Reported performance metrics included the precision, recall and F-measure, with support vector machine and Naïve Bayes being the best performing ML classifiers.ConclusionNLP and ML have emerged as an important tool for processing unstructured free text. Both supervised and unsupervised approaches have their role depending on the data source. With the advancement of data analysis tools, these techniques may be useful to healthcare organisations to generate insight from the volumes of unstructured free-text data.

scholarly journals Intelligent Detection of False Information in Arabic Tweets Utilizing Hybrid Harris Hawks Based Feature Selection and Machine Learning Models

Symmetry ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 556
Author(s):  
Thaer Thaher ◽  
Mahmoud Saheb ◽  
Hamza Turabieh ◽  
Hamouda Chantar
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Feature Selection ◽  
Language Processing ◽  
User Profile ◽  
Vital Role ◽  
Classification Model ◽  
Fake News ◽  
False Information ◽  
Social Media Platforms

Fake or false information on social media platforms is a significant challenge that leads to deliberately misleading users due to the inclusion of rumors, propaganda, or deceptive information about a person, organization, or service. Twitter is one of the most widely used social media platforms, especially in the Arab region, where the number of users is steadily increasing, accompanied by an increase in the rate of fake news. This drew the attention of researchers to provide a safe online environment free of misleading information. This paper aims to propose a smart classification model for the early detection of fake news in Arabic tweets utilizing Natural Language Processing (NLP) techniques, Machine Learning (ML) models, and Harris Hawks Optimizer (HHO) as a wrapper-based feature selection approach. Arabic Twitter corpus composed of 1862 previously annotated tweets was utilized by this research to assess the efficiency of the proposed model. The Bag of Words (BoW) model is utilized using different term-weighting schemes for feature extraction. Eight well-known learning algorithms are investigated with varying combinations of features, including user-profile, content-based, and words-features. Reported results showed that the Logistic Regression (LR) with Term Frequency-Inverse Document Frequency (TF-IDF) model scores the best rank. Moreover, feature selection based on the binary HHO algorithm plays a vital role in reducing dimensionality, thereby enhancing the learning model’s performance for fake news detection. Interestingly, the proposed BHHO-LR model can yield a better enhancement of 5% compared with previous works on the same dataset.

Is the equalization/normalization lens dead? Social media campaigning in US congressional elections

2018 ◽  
Vol 42 (5) ◽  
pp. 718-731 ◽  
Author(s):  
Jason Gainous ◽  
Andrew Segal ◽  
Kevin Wagner
Keyword(s):  
Social Media ◽  
Design Methodology ◽  
Power Structure ◽  
Congressional Elections ◽  
Campaign Spending ◽  
Interactive Effects ◽  
Content Type ◽  
Electoral Success ◽  
The Masses ◽  
Practical Implications

Purpose Early information technology scholarship centered on the internet’s potential to be a democratizing force was often framed using an equalization/normalization lens arguing that either the internet was going to be an equalizing force bringing power to the masses, or it was going to be normalized into the existing power structure. The purpose of this paper is to argue that considered over time the equalization/normalization lens still sheds light on our understanding of how social media (SM) strategy can shape electoral success asking if SM are an equalizing force balancing the resource gap between candidates or are being normalized into the modern campaign. Design/methodology/approach SM metrics and electoral data were collected for US congressional candidates in 2012 and 2016. A series of additive and interactive models are employed to test whether the effects of SM reach on electoral success are conditional on levels of campaign spending. Findings The results suggest that those candidates who spend more actually get more utility for their SM campaign than those who spend less in 2012. However, by 2016, spending inversely correlates with SM campaign utility. Research limitations/implications The findings indicate that SM appeared to be normalizing into the modern congressional campaign in 2012. However, with higher rates of penetration and greater levels of usage in 2016, the SM campaign utility was not a result of higher spending. SM may be a greater equalizing force now. Practical implications Campaigns that initially integrate digital and traditional strategies increase the effectiveness of the SM campaign because the non-digital strategy both complements and draws attention to the SM campaign. However, by 2016 the SM campaign was not driven by its relation to traditional campaign spending. Originality/value This is the first large N study to examine the interactive effects of SM reach and campaign spending on electoral success.

Feasibility study of automatically performing the concrete delivery dispatching through machine learning techniques

2015 ◽  
Vol 22 (5) ◽  
pp. 573-590 ◽  
Author(s):  
Mojtaba Maghrebi ◽  
Claude Sammut ◽  
S. Travis Waller
Keyword(s):  
Machine Learning ◽  
Human Resources ◽  
Design Methodology ◽  
Machine Learning Techniques ◽  
Mixing Process ◽  
Content Type ◽  
Practical Solution ◽  
Learning Techniques ◽  
Ready Mixed Concrete ◽  
Practical Implications

Purpose – The purpose of this paper is to study the implementation of machine learning (ML) techniques in order to automatically measure the feasibility of performing ready mixed concrete (RMC) dispatching jobs. Design/methodology/approach – Six ML techniques were selected and tested on data that was extracted from a developed simulation model and answered by a human expert. Findings – The results show that the performance of most of selected algorithms were the same and achieved an accuracy of around 80 per cent in terms of accuracy for the examined cases. Practical implications – This approach can be applied in practice to match experts’ decisions. Originality/value – In this paper the feasibility of handling complex concrete delivery problems by ML techniques is studied. Currently, most of the concrete mixing process is done by machines. However, RMC dispatching still relies on human resources to complete many tasks. In this paper the authors are addressing to reconstruct experts’ decisions as only practical solution.

When social media met commerce: a model of perceived customer value in group-buying

2016 ◽  
Vol 30 (4) ◽  
pp. 398-410 ◽  
Author(s):  
Yong-Ki Lee ◽  
Sally Y. Kim ◽  
Namho Chung ◽  
Kwanghoon Ahn ◽  
Jong-Won Lee
Keyword(s):  
Social Media ◽  
Least Squares ◽  
Significant Influence ◽  
Customer Value ◽  
Design Methodology ◽  
Social Commerce ◽  
Research Directions ◽  
Content Type ◽  
Group Buying ◽  
Perceived Customer Value

Purpose Social commerce using social media has been on the rapid increase. Among various social commerce models, group-buying has become the mainstream. There is a paucity of research related to how customers perceive value in group-buying situations. This paper aims to examine and analyze various factors that influence perceived customer value in group-buying. Design/methodology/approach Data were collected using a survey on customers who had purchased a restaurant service deal on a group-buying site. A partial least squares technique was used to estimate the model. Findings Results show that perceived customer value affects customers’ group buying intentions and that all four antecedents of perceived value (low price, valence of experience, trust in social media and reputation of the group-buying site) have a significant influence. Implications and further research directions are discussed at the end of the paper. Originality/value This study provides valuable strategic implications for social commerce firms.

Stairways to heaven: implementing social media in organizations

2013 ◽  
Vol 17 (5) ◽  
pp. 741-754 ◽  
Author(s):  
Moria Levy
Keyword(s):  
Social Media ◽  
Knowledge Management ◽  
Empirical Study ◽  
Design Methodology ◽  
Applied Research ◽  
Service Marketing ◽  
Content Type ◽  
Four Levels ◽  
Functional Components ◽  
Practical Implications

Purpose – This paper is aimed at both researchers and organizations. For researchers, it seeks to provide a means for better analyzing the phenomenon of social media implementation in organizations as a knowledge management (KM) enabler. For organizations, it seeks to suggest a step-by-step architecture for practically implementing social media and benefiting from it in terms of KM. Design/methodology/approach – The research is an empirical study. A hypothesis was set; empirical evidence was collected (from 34 organizations). The data were analyzed both quantitatively and qualitatively, thereby forming the basis for the proposed architecture. Findings – Implementing social media in organizations is more than a yes/no question; findings show various levels of implementation in organizations: some implementing at all levels, while others implement only tools, functional components, or even only visibility. Research limitations/implications – Two main themes should be further tested: whether the suggested architecture actually yields faster/eased KM implementation compared to other techniques; and whether it can serve needs beyond the original scope (KM, Israel) as tested in this study (i.e. also for other regions and other needs – service, marketing and sales, etc.). Practical implications – Organizations can use the suggested four levels architecture as a guideline for implementing social media as part of their KM efforts. Originality/value – This paper is original and innovative. Previous studies describe the implementation of social media in terms of yes/no; this research explores the issue as a graded one, where organizations can and do implement social media step-by-step. The paper's value is twofold: it can serve as a foundational study for future researches, which can base their analysis on the suggested architecture of four levels of implementation. It also serves as applied research that will help organizations searching for social media implementation KM enablers.

AI and libraries: trends and projections

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Adetoun A. Oyelude
Keyword(s):  
Language Processing ◽  
Service Provision ◽  
Design Methodology ◽  
Human Robot Interaction ◽  
Human Intelligence ◽  
Library Service ◽  
Robot Interaction ◽  
Content Type ◽  
New Horizons ◽  
Advanced Technologies

Purpose This paper aims to focus on the trends and projection for future use of artificial intelligence (AI) in libraries. AI technologies is the latest among the technologies being used in libraries. The technology has systems that have natural language processing, machine learning and pattern recognition capabilities that make service provision easier for libraries. Design/methodology/approach Systematic literature review is done, exploring blogs and wikis, to collect information on the ways in which AI is used and can be futuristically used in libraries. Findings This paper found that uses of AI in libraries entailed enhanced services such as content indexing, document matching, content mapping content summarization and many others. AI possibilities were also found to include improving the technology of gripping, localizing and human–robot interaction and also having artificial superintelligence, the hypothetical AI that surpasses human intelligence and abilities. Originality/value It is concluded that advanced technologies that AI are, will help librarians to open up new horizons and solve challenges that crop up in library service delivery.

Is this mine? Psychological ownership and the social media follower

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Caroline S.L. Tan
Keyword(s):  
Social Media ◽  
Design Methodology ◽  
Vital Role ◽  
Psychological Ownership ◽  
Structured Interviews ◽  
Content Type ◽  
Face To Face ◽  
The Social ◽  
Social Currency ◽  
Different Levels

Purpose The purpose of this study is to examine psychological ownership (PO) experienced by followers of social media influencers toward both influencer and the product. Design/methodology/approach Data were collected using face-to-face semi-structured interviews that were conducted with 30 respondents and analyzed using thematic analysis. Findings The study demonstrated that the PO experienced by the follower changes under different conditions resulting from perceived value, social currency and follower activity. Social currency plays a vital role in determining the target of PO, often affecting the narrative by the follower. Originality/value To the best of the author’s knowledge, this is the first paper to examine the transference of PO between product and influencer as experienced by the follower. It provides an understanding on PO that is experienced in different levels of intensity and changes depending on the motive of the follower; hence, transference of PO occurs and it is not a static.

From campfire to coliseum: motivations for using social networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Paula Castro Pires de Souza Chimenti ◽  
Marco Aurelio de Souza Rodrigues ◽  
Marcelo Guedes Carneiro ◽  
Roberta Dias Campos
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Exploratory Study ◽  
Design Methodology ◽  
Qualitative Approach ◽  
Content Type ◽  
Media Usage ◽  
Practical Implications ◽  
Collective Narrative

Purpose Through a literature review, a gap has been identified regarding the role of competition as a driver of social network (SN) usage. This study aims to design to address this gap, seeking motivators for SN usage based on how SN consumption may be related to users’ experience of competition. Therefore, the purpose of this study is to investigate the influence of competition in social media usage. Design/methodology/approach The authors used an exploratory qualitative approach, conducting a set of focus groups with young social media users. Data was analyzed with software. Findings Two new drivers for SN use are proposed, namely, competition and collective narrative. Research limitations/implications This is an exploratory study, and it does not seek to generalize results or quantify causal relationships among variables. Practical implications This paper offers SN managers a deeper understanding of key growth drivers for these media. Social implications This research can help society understand and debate the impacts of SNs on users’ lives, providing insights into drivers of excessive usage. Originality/value This paper proposes the following two SN usage drivers yet to be described in the literature: competition and collective narrative.

Sign in / Sign up

Export Citation Format

Share Document