scholarly journals Visualization of job availability based on text analytics localization approach

2019 ◽  
Vol 16 (2) ◽  
pp. 744
Author(s):  
Nur Azmina Mohamad Zamani ◽  
Norhaslinda Kamaruddin ◽  
Abdul Wahab ◽  
Nur Shahana Saat
Keyword(s):  
Social Media ◽  
Geographical Location ◽  
Relevant Information ◽  
Text Analytics ◽  
Job Seekers ◽  
Potential Employer ◽  
Additional Information ◽  
Job Advertisement ◽  
Job Searching ◽  
Job Location

<span>Rate of employment is a strong indicator of economic stability of a country. It relates to the number of volumes of produced products and services. If the unemployment rate is high, the amount of gross domestic product (GDP) of a country may be declined. One of the main factors that contributes to low rate of employment is the mismatch between job seeker and the requirement of the job applied.  This is due to the limited analysis performed on the relevant information on job advertisement; such as, skills, responsibilities of the job, location and expectation of the employers. The obscure job descriptions provided in the advertisement may result in application of unsuitable candidates that can cause rejection of the candidate and the potential employer may take a long time to filter and evaluate the applications. A system that is able to provide relevant information in a simple and catchy way is needed to simplify the task of job searching. In this paper we proposed a text analytics technique to extract users’ comments from social media such as Twitter and Facebook on job advertisement. The result is then displayed in a geotagged map that can reveal the density of job availability based on geographical location. The job seekers can easily observe and select their desired job location. The initial system shows potential of the inclusion of the proposed approach in job advertisement websites. In comparison to other job searching websites, this system can provide additional information on public view about the advertised job obtained from the social media text analytics. With this additional information, jobseekers have more confidence in job selection and allows employers to receive more suitable candidates for the available positions. It is hoped that the proposed system can tailor the job advertisements to the need of the jobseeker and making the job application more relevant hence reducing the potential employers’ processing time.</span>

Worker word of mouth on the internet

2016 ◽  
Vol 37 (4) ◽  
pp. 709-723 ◽  
Author(s):  
Santiago Melián-González ◽  
Jacques Bulchand-Gidumal
Keyword(s):  
Social Media ◽  
Word Of Mouth ◽  
Relevant Information ◽  
Employee Attitudes ◽  
The Internet ◽  
Job Seekers ◽  
Organizational Image ◽  
Content Type ◽  
Work Related ◽  
Current Spread

Purpose – The purpose of this paper is to analyze the consequences of an unexplored and real worker behavior on the internet (worker electronic word of mouth (weWOM)) for human resource image, as well as to analyze its impact on job seekers and employee’s intentions and attitudes. Design/methodology/approach – The research objectives were tested through a web-based experiment based on real weWOM. Through a self-selected sample procedure, 238 individuals were exposed to three types of weWOM: positive, negative, and intermediate. Findings – Depending on the kind of weWOM people see on the internet, perceived HR image changes. Positive, intermediate, and negative weWOM produce different behavioral intentions with respect to different recruiting aspects. weWOM also influences two important employee attitudes and resulted more credible than firms’ recognitions. Research limitations/implications – The sample is a convenience one. Since managers may be reluctant to admit weWOM’s credibility the relationship between weWOM and other employees’ attitudes data should be analyzed. Practical implications – weWOM may constitute an indicator for anticipating applicants’ key behavior (intention to apply, intention to recommend a company, and compensation demands). In order to stimulate it companies should generate relevant information about the most common categories of weWOM and place it on the employer review websites. Additionally, if weWOM is positive it can be used to create a positive external constructed image among the staff. Social implications – weWOM is a current phenomenon without information about its implications. Most of the websites that host it are free accessible. This research offers specific data about how people react to it. Originality/value – Employer review websites are probably the preferred channels to express work-related WOM. Nevertheless the current spread of the internet only one study has been conducted about it. This research fits in the current social media age and sheds new information about this kind of communication. The findings contribute to strengthen the theory about how organizational image is built showing that WOM and social media exposure are significant determinants of two types of organizational images. Also we contribute to the theory about recruitment showing detailed information regarding what may occurs during the first phases of this practice.

Measuring Relevant Information in Health Social Network Conversations and Clinical Diagnosis Cases (Preprint)

2018 ◽  
Author(s):  
Albert Moreira ◽  
Raul Alonso-Calvo ◽  
Alberto Muñoz ◽  
Jose Crespo
Keyword(s):  
Social Media ◽  
Social Network ◽  
Relevant Information ◽  
Online Discussions ◽  
Biomedical Knowledge ◽  
Expert Opinions ◽  
Health Related ◽  
Health Social Network ◽  
Discussion System ◽  
Clinical Cases

BACKGROUND Internet and Social media is an enormous source of information. Health Social Networks and online collaborative environments enable users to create shared content that afterwards can be discussed. While social media discussions for health related matters constitute a potential source of knowledge, characterizing the relevance of participations from different users is a challenging task. OBJECTIVE The aim of this paper is to present a methodology designed for quantifying relevant information provided by different participants in clinical online discussions. METHODS A set of key indicators for different aspects of clinical conversations and specific clinical contributions within a discussion have been defined. These indicators make use of biomedical knowledge extraction based on standard terminologies and ontologies. These indicators allow measuring the relevance of information of each participant of the clinical conversation. RESULTS Proposed indicators have been applied to two discussions extracted from PatientsLikeMe, as well as to two real clinical cases from the Sanar collaborative discussion system. Results obtained from indicators in the tested cases have been compared with clinical expert opinions to check indicators validity. CONCLUSIONS The methodology has been successfully used for describing participant interactions in real clinical cases belonging to a collaborative clinical case discussion tool and from a conversation from a Health Social Network.

scholarly journals Improving Topic Coherence Using Entity Extraction Denoising

2018 ◽  
Vol 110 (1) ◽  
pp. 85-101 ◽  
Author(s):  
Ronald Cardenas ◽  
Kevin Bello ◽  
Alberto Coronado ◽  
Elizabeth Villota
Keyword(s):  
Topic Modeling ◽  
Human Perception ◽  
Relevant Information ◽  
Entity Recognition ◽  
Entity Extraction ◽  
Fine Grained ◽  
Job Advertisement ◽  
Coherence Score ◽  
Probabilistic Topic Modeling ◽  
Promising Solution

Abstract Managing large collections of documents is an important problem for many areas of science, industry, and culture. Probabilistic topic modeling offers a promising solution. Topic modeling is an unsupervised machine learning method and the evaluation of this model is an interesting problem on its own. Topic interpretability measures have been developed in recent years as a more natural option for topic quality evaluation, emulating human perception of coherence with word sets correlation scores. In this paper, we show experimental evidence of the improvement of topic coherence score by restricting the training corpus to that of relevant information in the document obtained by Entity Recognition. We experiment with job advertisement data and find that with this approach topic models improve interpretability in about 40 percentage points on average. Our analysis reveals as well that using the extracted text chunks, some redundant topics are joined while others are split into more skill-specific topics. Fine-grained topics observed in models using the whole text are preserved.

scholarly journals Job Seekers’ Self-Directed Learning Activities Explained Through the Lens of Regulatory Focus

2021 ◽  
pp. 089484532199164
Author(s):  
Adam M. Kanar ◽  
Dave Bouckenooghe
Keyword(s):  
Job Search ◽  
Regulatory Focus ◽  
Self Efficacy ◽  
Learning Activities ◽  
Job Seekers ◽  
Self Directed Learning ◽  
Significant Relationships ◽  
Directed Learning ◽  
Job Searching

This study aimed to understand the role of regulatory focus for influencing self-directed learning activities during a job search. The authors surveyed 185 job-searching university students at two time points to explore the conditions under which regulatory focus (promotion and prevention foci) impacts self-directed learning activities and the number of employment interviews secured. Both promotion and prevention foci showed significant relationships with self-directed learning activities and number of interviews, and positive and negative affect partially mediated these relationships. The relationships between both regulatory focus strategies and self-directed learning were also contingent on self-efficacy. More specifically, prevention focus and self-directed learning showed a positive relationship for job seekers with high levels of self-efficacy but a negative one for job seekers with low levels of self-efficacy. This research extends the understanding of the role of regulatory focus in the context of self-directed learning during a job search. Implications for research and practice are discussed.

scholarly journals Maximizing Acceleration and Change of Direction in Sport: A Case Series to Illustrate How the Force-Velocity Profile Provides Additional Information to That Derived from Linear Sprint Time

2021 ◽  
Vol 18 (11) ◽  
pp. 6140
Author(s):  
Andrés Baena-Raya ◽  
Manuel A. Rodríguez-Pérez ◽  
Pedro Jiménez-Reyes ◽  
Alberto Soriano-Maldonado
Keyword(s):  
Mechanical Properties ◽  
Case Series ◽  
Relevant Information ◽  
Maximal Power Output ◽  
Sprint Time ◽  
Change Of Direction ◽  
Training Interventions ◽  
Additional Information ◽  
Technical Report ◽  
Force Velocity

Sprint running and change of direction (COD) present similar mechanical demands, involving an acceleration phase in which athletes need to produce and apply substantial horizontal external force. Assessing the mechanical properties underpinning individual sprint acceleration might add relevant information about COD performance in addition to that obtained through sprint time alone. The present technical report uses a case series of three athletes with nearly identical 20 m sprint times but with different mechanical properties and COD performances. This makes it possible to illustrate, for the first time, a potential rationale for why the sprint force-velocity (FV) profile (i.e., theoretical maximal force (F0), velocity (V0), maximal power output (Pmax), ratio of effective horizontal component (RFpeak) and index of force application technique (DRF)) provides key information about COD performance (i.e., further to that derived from simple sprint time), which can be used to individualize training. This technical report provides practitioners with a justification to assess the FV profile in addition to sprint time when the aim is to enhance sprint acceleration and COD performance; practical interpretations and advice on how training interventions could be individualized based on the athletes’ differential sprint mechanical properties are also specified.

scholarly journals Predicting Implicit User Preferences with Multimodal Feature Fusion for Similar User Recommendation in Social Media

2021 ◽  
Vol 11 (3) ◽  
pp. 1064
Author(s):  
Jenq-Haur Wang ◽  
Yen-Tsang Wu ◽  
Long Wang
Keyword(s):  
Social Media ◽  
Feature Fusion ◽  
Relevant Information ◽  
Image Features ◽  
User Preferences ◽  
User Preference ◽  
Late Fusion ◽  
Multimodal Features ◽  
Fusion Methods ◽  
Text Features

In social networks, users can easily share information and express their opinions. Given the huge amount of data posted by many users, it is difficult to search for relevant information. In addition to individual posts, it would be useful if we can recommend groups of people with similar interests. Past studies on user preference learning focused on single-modal features such as review contents or demographic information of users. However, such information is usually not easy to obtain in most social media without explicit user feedback. In this paper, we propose a multimodal feature fusion approach to implicit user preference prediction which combines text and image features from user posts for recommending similar users in social media. First, we use the convolutional neural network (CNN) and TextCNN models to extract image and text features, respectively. Then, these features are combined using early and late fusion methods as a representation of user preferences. Lastly, a list of users with the most similar preferences are recommended. The experimental results on real-world Instagram data show that the best performance can be achieved when we apply late fusion of individual classification results for images and texts, with the best average top-k accuracy of 0.491. This validates the effectiveness of utilizing deep learning methods for fusing multimodal features to represent social user preferences. Further investigation is needed to verify the performance in different types of social media.

scholarly journals When more is more: redundant modifiers can facilitate visual search

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Gwendolyn Rehrig ◽  
Reese A. Cullimore ◽  
John M. Henderson ◽  
Fernanda Ferreira
Keyword(s):  
Visual Search ◽  
Real World ◽  
Search Space ◽  
Relevant Information ◽  
Target Object ◽  
Search Performance ◽  
Redundant Information ◽  
Additional Information ◽  
Target Template ◽  
Template Specificity

Abstract According to the Gricean Maxim of Quantity, speakers provide the amount of information listeners require to correctly interpret an utterance, and no more (Grice in Logic and conversation, 1975). However, speakers do tend to violate the Maxim of Quantity often, especially when the redundant information improves reference precision (Degen et al. in Psychol Rev 127(4):591–621, 2020). Redundant (non-contrastive) information may facilitate real-world search if it narrows the spatial scope under consideration, or improves target template specificity. The current study investigated whether non-contrastive modifiers that improve reference precision facilitate visual search in real-world scenes. In two visual search experiments, we compared search performance when perceptually relevant, but non-contrastive modifiers were included in the search instruction. Participants (NExp. 1 = 48, NExp. 2 = 48) searched for a unique target object following a search instruction that contained either no modifier, a location modifier (Experiment 1: on the top left, Experiment 2: on the shelf), or a color modifier (the black lamp). In Experiment 1 only, the target was located faster when the verbal instruction included either modifier, and there was an overall benefit of color modifiers in a combined analysis for scenes and conditions common to both experiments. The results suggest that violations of the Maxim of Quantity can facilitate search when the violations include task-relevant information that either augments the target template or constrains the search space, and when at least one modifier provides a highly reliable cue. Consistent with Degen et al. (2020), we conclude that listeners benefit from non-contrastive information that improves reference precision, and engage in rational reference comprehension. Significance statement This study investigated whether providing more information than someone needs to find an object in a photograph helps them to find that object more easily, even though it means they need to interpret a more complicated sentence. Before searching a scene, participants were either given information about where the object would be located in the scene, what color the object was, or were only told what object to search for. The results showed that providing additional information helped participants locate an object in an image more easily only when at least one piece of information communicated what part of the scene the object was in, which suggests that more information can be beneficial as long as that information is specific and helps the recipient achieve a goal. We conclude that people will pay attention to redundant information when it supports their task. In practice, our results suggest that instructions in other contexts (e.g., real-world navigation, using a smartphone app, prescription instructions, etc.) can benefit from the inclusion of what appears to be redundant information.

Triage and diagnosis of COVID-19 from medical social media (Preprint)

2021 ◽  
Author(s):  
Abul Hasan ◽  
Mark Levene ◽  
David Weston ◽  
Renate Fromson ◽  
Nicolas Koslover ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Learning Models ◽  
Rule Based ◽  
Additional Information ◽  
Processing Pipeline ◽  
Machine Learning Models

BACKGROUND The COVID-19 pandemic has created a pressing need for integrating information from disparate sources, in order to assist decision makers. Social media is important in this respect, however, to make sense of the textual information it provides and be able to automate the processing of large amounts of data, natural language processing methods are needed. Social media posts are often noisy, yet they may provide valuable insights regarding the severity and prevalence of the disease in the population. In particular, machine learning techniques for triage and diagnosis could allow for a better understanding of what social media may offer in this respect. OBJECTIVE This study aims to develop an end-to-end natural language processing pipeline for triage and diagnosis of COVID-19 from patient-authored social media posts, in order to provide researchers and other interested parties with additional information on the symptoms, severity and prevalence of the disease. METHODS The text processing pipeline first extracts COVID-19 symptoms and related concepts such as severity, duration, negations, and body parts from patients’ posts using conditional random fields. An unsupervised rule-based algorithm is then applied to establish relations between concepts in the next step of the pipeline. The extracted concepts and relations are subsequently used to construct two different vector representations of each post. These vectors are applied separately to build support vector machine learning models to triage patients into three categories and diagnose them for COVID-19. RESULTS We report that Macro- and Micro-averaged F_{1\ }scores in the range of 71-96% and 61-87%, respectively, for the triage and diagnosis of COVID-19, when the models are trained on human labelled data. Our experimental results indicate that similar performance can be achieved when the models are trained using predicted labels from concept extraction and rule-based classifiers, thus yielding end-to-end machine learning. Also, we highlight important features uncovered by our diagnostic machine learning models and compare them with the most frequent symptoms revealed in another COVID-19 dataset. In particular, we found that the most important features are not always the most frequent ones. CONCLUSIONS Our preliminary results show that it is possible to automatically triage and diagnose patients for COVID-19 from natural language narratives using a machine learning pipeline, in order to provide additional information on the severity and prevalence of the disease through the eyes of social media.

Older and Younger Job Seekers' Impression Management on LinkedIn

2021 ◽  
Vol 20 (2) ◽  
pp. 61-74
Author(s):  
Franciska Krings ◽  
Irina Gioaba ◽  
Michèle Kaufmann ◽  
Sabine Sczesny ◽  
Leslie Zebrowitz
Keyword(s):  
Social Media ◽  
Social Networking ◽  
Impression Management ◽  
Social Networking Sites ◽  
The Internet ◽  
Job Seekers ◽  
Self Presentation ◽  
Job Offers ◽  
Research Show

Abstract. The use of social networking sites such as LinkedIn in recruitment is ubiquitous. This practice may hold risks for older job seekers. Not having grown up using the internet and having learned how to use social media only in middle adulthood may render them less versed in online self-presentation than younger job seekers. Results of this research show some differences and many similarities between younger and older job seekers' impression management on their LinkedIn profiles. Nevertheless, independent of their impression management efforts, older job seekers received fewer job offers than younger job seekers. Only using a profile photo with a younger appearance reduced this bias. Implications for the role of job seeker age in online impression management and recruitment are discussed.

TECHNOLOGY ADOPTION AND ADAPTATION TO CLIMATE CHANGE — A CASE-BASED APPROACH

2012 ◽  
Vol 03 (02) ◽  
pp. 1250007 ◽  
Author(s):  
JÜRGEN EICHBERGER ◽  
ANI GUERDJIKOVA
Keyword(s):  
New Technologies ◽  
New Technology ◽  
Relevant Information ◽  
Adaptation To Climate Change ◽  
Climate Conditions ◽  
Technology Learning ◽  
The Public ◽  
Additional Information ◽  
Technological Adaptation ◽  
Long Run

We present a model of technological adaptation in response to a change in climate conditions. The main feature of the model is that new technologies are not just risky, but also ambiguous. Pessimistic agents are thus averse to adopting a new technology. Learning is induced by optimists, who are willing to try out technologies about which there is little evidence available. We show that both optimists and pessimists are crucial for a successful adaptation. While optimists provide the public good of information which gives pessimists an incentive to innovate, pessimists choose the new technology persistently in the long-run which increases the average returns for the society. Hence, the optimal share of optimists in the society is strictly positive. When the share of optimists in the society is too low, innovation is slow and the obtained steady-state is inefficient. We discuss two policies which can potentially alleviate this inefficiency: Subsidies and provision of additional information. We show that if precise and relevant information is available, pessimists would be willing to pay for it and consequently adopt the new technology. Hence, providing information might be a more efficient policy, which is both self-financing and results in better social outcomes.

Sign in / Sign up

Export Citation Format

Share Document