scholarly journals Text Mining Data from Students to Reveal Meaningful Information for Educators

2021 ◽  
Vol 24 (1) ◽  
pp. 5-30
Author(s):  
Zainab M. AlQenaei ◽  
David E. Monarchi
Keyword(s):  
Text Mining ◽  
Learning Strategies ◽  
Undergraduate Students ◽  
Text Analysis ◽  
Past Research ◽  
Text Data ◽  
Final Grade ◽  
Meaningful Information ◽  
Novel Approach ◽  
Academic Profiles

Academic institutions adopt different advising tools for various objectives. Past research used both numeric and text data to predict students’ performance. Moreover, numerous research projects have been conducted to find different learning strategies and profiles of students. Those strategies of learning together with academic profiles assisted in the advising process. This research proposes an approach to supplement these activities by text mining students’ essays to better understand different students’ profiles across different courses (subjects). Text analysis was performed on 99 essays written by undergraduate students in three different courses. The essays and terms were projected in a 20-dimensional vector space. The 20 dimensions were used as independent variables in a regression analysis to predict a student’s final grade in a course. Further analyses were performed on the dimensions found statistically significant. This study is a preliminary analysis to demonstrate a novel approach of extracting meaningful information by text mining essays written by students to develop an advising tool that can be used by educators.

scholarly journals Ternary Classification of Product Based Reviews: Survey, Open Issues and New Approach for Sentiment Analysis

2021 ◽  
Vol 1 (2) ◽  
pp. 1-8
Author(s):  
Sushila Sonare ◽  
Megha Kamble
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Text Analysis ◽  
Text Data ◽  
New Approach ◽  
Meaningful Information ◽  
Multi Class Classification ◽  
Almost All ◽  
Open Issues

Now-a-days, it is very common that the customers share their thoughts about any product, brand and their experience in social media. The analysts collect these reviews and process it, to extract meaningful information about the product. The beauty of social media is, it’s involved in all the domains. So the analysts got reviews from different social media and platforms for almost all kind of thing. The Sentiment Analysis is applied to predict outcomes for getting useful information, for ex.; like predict the blockbuster for a movie, rating for any new launches and many more. This type of prediction is really helpful for the customer to buy any goods or take any services in this competitive world. This paper is focused on e-commerce website reviews which are normally in text form with some special characters and some symbols (emojis). Each word in this text set got some meaning in terms of context, emotion and prior experience. These characteristics contribute to some of the features of text data for prediction. The objective of this paper is to compile existing research works on text analysis and emotion based analysis. The open issues and challenges of document based sentiment analysis are also discussed. The paper concluded with proposing a new approach of multi class classification. Ternary classification for classes positive, negative and neutral is suggested primarily for product based text and emoji reviews on Twitter social media.

scholarly journals Ternary Classification of Product Based Reviews: Survey, Open Issues and New Approach for Sentiment Analysis

2021 ◽  
pp. 1-8
Author(s):  
Sushila Sonare ◽  
◽  
Dr. Megha Kamble ◽  
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Text Analysis ◽  
Text Data ◽  
New Approach ◽  
Meaningful Information ◽  
Multi Class Classification ◽  
Almost All ◽  
Open Issues

Now-a-days, it is very common that the customers share their thoughts about any product, brand and their experience in social media. The analysts collect these reviews and process it, to extract meaningful information about the product. The beauty of social media is, it’s involved in all the domains. So the analysts got reviews from different social media and platforms for almost all kind of thing. The Sentiment Analysis is applied to predict outcomes for getting useful information, for ex.; like predict the blockbuster for a movie, rating for any new launches and many more. This type of prediction is really helpful for the customer to buy any goods or take any services in this competitive world. This paper is focused on e-commerce website reviews which are normally in text form with some special characters and some symbols (emojis). Each word in this text set got some meaning in terms of context, emotion and prior experience. These characteristics contribute to some of the features of text data for prediction. The objective of this paper is to compile existing research works on text analysis and emotion based analysis. The open issues and challenges of document based sentiment analysis are also discussed. The paper concluded with proposing a new approach of multi class classification. Ternary classification for classes positive, negative and neutral is suggested primarily for product based text and emoji reviews on Twitter social media.

scholarly journals Building Causal Graphs from Medical Literature and Electronic Medical Records

2019 ◽  
Vol 33 ◽  
pp. 1102-1109
Author(s):  
Galia Nordon ◽  
Gideon Koren ◽  
Varda Shalev ◽  
Benny Kimelfeld ◽  
Uri Shalit ◽  
...  
Keyword(s):  
Text Analysis ◽  
Medical Literature ◽  
Causal Relationships ◽  
Text Data ◽  
Domain Experts ◽  
Causal Connections ◽  
Novel Approach ◽  
Confounding Variables ◽  
Causal Graphs ◽  
Effective Analysis

Large repositories of medical data, such as Electronic Medical Record (EMR) data, are recognized as promising sources for knowledge discovery. Effective analysis of such repositories often necessitate a thorough understanding of dependencies in the data. For example, if the patient age is ignored, then one might wrongly conclude a causal relationship between cataract and hypertension. Such confounding variables are often identified by causal graphs, where variables are connected by causal relationships. Current approaches to automatically building such graphs are based on text analysis over medical literature; yet, the result is typically a large graph of low precision. There are statistical methods for constructing causal graphs from observational data, but they are less suitable for dealing with a large number of covariates, which is the case in EMR data. Consequently, confounding variables are often identified by medical domain experts via a manual, expensive, and time-consuming process. We present a novel approach for automatically constructing causal graphs between medical conditions. The first part is a novel graph-based method to better capture causal relationships implied by medical literature, especially in the presence of multiple causal factors. Yet even after using these advanced text-analysis methods, the text data still contains many weak or uncertain causal connections. Therefore, we construct a second graph for these terms based on an EMR repository of over 1.5M patients. We combine the two graphs, leaving only edges that have both medical-text-based and observational evidence. We examine several strategies to carry out our approach, and compare the precision of the resulting graphs using medical experts. Our results show a significant improvement in the precision of any of our methods compared to the state of the art.

scholarly journals Parliamentary Mandate Fulfilment. An automated approach to measuring congruence between the pre and post-electoral discourse of parties using word embeddings

2021 ◽  
Author(s):  
Yani Kartalis
Keyword(s):  
Social Sciences ◽  
Computational Linguistics ◽  
Text Analysis ◽  
Electoral Competition ◽  
Past Research ◽  
Word Embeddings ◽  
Recent Advances ◽  
Novel Approach ◽  
The Social ◽  
Electoral Rhetoric

The idea that electoral competition, party promises and manifestos are important for how the representative behaviour of parties unfolds post-electorally is central to democratic theories of representation. Scholars of Party Mandate fulfilment have for long been focusing methodologically on the number of pre-electoral pledges parties in government manage to realize. This paper analyses existing research and its limitations and proposes a novel approach for mandate fulfilment, extending past research (both conceptually and methodologically) by looking at the extent to which the parliamentary discourse of parties matches their electoral discourse. It designs, tentatively validates and implements a novel measure of how similar is the pre and post-electoral rhetoric of parties by utilizing recent advances in computational linguistics and the diffusion of text analysis tools in the social sciences. It applies it on the Irish parliament and compares electoral manifesto data with post-electoral parliamentary data from 1997 to 2019.

China's Newsmakers: Official Media Coverage and Political Shifts in the Xi Jinping Era

2017 ◽  
Vol 233 ◽  
pp. 111-136 ◽  
Author(s):  
Kyle Jaros ◽  
Jennifer Pan
Keyword(s):  
Text Analysis ◽  
Media Coverage ◽  
Past Research ◽  
Early Years ◽  
Xi Jinping ◽  
Political Actors ◽  
Party Organizations ◽  
Automated Text Analysis ◽  
The Media ◽  
Party Dominance

AbstractXi Jinping's rise to power in late 2012 brought immediate political realignments in China, but the extent of these shifts has remained unclear. In this paper, we evaluate whether the perceived changes associated with Xi Jinping's ascent – increased personalization of power, centralization of authority, Party dominance and anti-Western sentiment – were reflected in the content of provincial-level official media. As past research makes clear, media in China have strong signalling functions, and media coverage patterns can reveal which actors are up and down in politics. Applying innovations in automated text analysis to nearly two million newspaper articles published between 2011 and 2014, we identify and tabulate the individuals and organizations appearing in official media coverage in order to help characterize political shifts in the early years of Xi Jinping's leadership. We find substantively mixed and regionally varied trends in the media coverage of political actors, qualifying the prevailing picture of China's “new normal.” Provincial media coverage reflects increases in the personalization and centralization of political authority, but we find a drop in the media profile of Party organizations and see uneven declines in the media profile of foreign actors. More generally, we highlight marked variation across provinces in coverage trends.

Anxiety in reading and listening English as a foreign language in Chinese undergraduate students

2017 ◽  
Vol 22 (6) ◽  
pp. 719-738 ◽  
Author(s):  
Bonnie Wing-Yin Chow ◽  
Hey Tou Chiu ◽  
Simpson W. L. Wong
Keyword(s):  
Foreign Language ◽  
Language Learning ◽  
Learning Strategies ◽  
Undergraduate Students ◽  
Learning Motivation ◽  
Behavioral Correlates ◽  
Listening Anxiety ◽  
Mediation Analyses ◽  
Chinese Undergraduates ◽  
Efl Learning

This study tested relationships between foreign language (FL) reading and listening anxiety and learner variables in English as a foreign language (EFL). It tested links between foreign language anxiety (FLA) and its cognitive, affective and behavioral correlates in English (i.e. language learning strategies, learning motivation, and performance). Three-hundred-and-six Chinese undergraduates learning EFL were administered the measures via a questionnaire. Regression analyses indicated that EFL performance and EFL motivation were key factors that uniquely predicted EFL reading and listening anxiety. However, the role of EFL learning strategies was not significant after the effects of EFL performance and EFL motivation were controlled for. Despite this, mediation analyses revealed that EFL learning strategies had a significant indirect effect on EFL reading performance and listening anxiety levels with EFL learning motivation as a mediator. This suggests its secondary role in affecting FL anxieties. These findings provide important implications regarding assessment of students’ FL anxiety level as well as identification of and intervention for those with FL difficulties. These findings have extended past studies by highlighting the relative importance of these cognitive, affective and behavioral correlates on Chinese undergraduates’ EFL anxiety in specific domains.

Teachers’ Ontological Perspectives of Computational Thinking and Assessment: A Text Mining Approach

2021 ◽  
pp. 073563312110435
Author(s):  
Rina P.Y. Lai
Keyword(s):  
Text Mining ◽  
Online Survey ◽  
Computational Thinking ◽  
Hierarchical Cluster ◽  
Theory And Practice ◽  
Graph Theoretic ◽  
Novel Approach ◽  
Significant Step ◽  
Representation Method ◽  
A Minor

As a dynamic and multifaceted construct, computational thinking (CT) has proven to be challenging to conceptualize and assess, which impedes the development of a workable ontology framework. To address this issue, the current article describes a novel approach towards understanding the ontological aspects of CT by using text mining and graph-theoretic techniques to elucidate teachers’ perspectives collected in an online survey (N = 105). In particular, a hierarchical cluster analysis, a knowledge representation method, was applied to identify sub-groups in CT conceptualization and assessment amongst teachers. Five clusters in conceptualization and two clusters in assessment were identified; several relevant and distinct themes were also extracted. The results suggested that teachers attributed CT as a competence domain, relevant in the problem- solving context, as well as applicable and transferrable to various disciplines. The results also shed light on the importance of using multiple approaches to assess the diversity of CT. Overall, the findings collectively contributed to a comprehensive and multi-perspective representation of CT that refine both theory and practice. The methodology employed in this article has suggested a minor but significant step towards addressing the quintessential questions of “what is CT?” and “how is it evidenced?”.

An Empirical Study on Vocabulary Learning Strategies by Jordanian FFL University Students

2018 ◽  
Vol 63 (2) ◽  
pp. 294-315
Author(s):  
Reem Ibrahim Rabadi ◽  
Batoul Al-Muhaissen
Keyword(s):  
Learning Strategies ◽  
Language Learners ◽  
Undergraduate Students ◽  
Social Cognitive ◽  
Vocabulary Learning ◽  
Descriptive Analysis ◽  
Social Strategies ◽  
Vocabulary Learning Strategies ◽  
High Level ◽  
Individual Strategies

Abstract This study explores the use of Vocabulary Learning Strategies (VLSs) by Jordanian undergraduate students majoring French as a Foreign Language (FFL) at Jordanian universities. The vocabulary learning strategies (Memory, Determination, Social, Cognitive, and Metacognitive) were used in this study following Schmitt’s taxonomy. A five-point Likert-scale questionnaire containing 37 items adapted from Schmitt’s (1997) Vocabulary Learning Strategies Questionnaire (VLSQ) administered to 840 FFL undergraduates randomly selected from seven Jordanian universities. The descriptive analysis showed that the participants of the study regardless of their year of study were medium strategy users overall. The results revealed that Memory strategies were the most frequently employed strategies, whereas the Social strategies were the least frequently used ones. Although the participants were medium strategy users, the results of the VLSQ disclosed that some individual strategies were employed at a high level. Accordingly, detecting these strategies will be beneficial to language instructors to improve effective vocabulary teaching techniques and to motivate language learners to use them more frequently.

scholarly journals Text embedding using image steganography in spatial domain

2018 ◽  
Vol 7 (3.6) ◽  
pp. 1 ◽  
Author(s):  
P Srilakshmi ◽  
Ch Himabindu ◽  
N Chaitanya ◽  
S V. Muralidhar ◽  
M V. Sumanth ◽  
...  
Keyword(s):  
Text Message ◽  
Spatial Domain ◽  
Image Steganography ◽  
Text Data ◽  
Novel Approach

This paper proposed novel approach of image steganography for text embedding in spatial domain. In the proposed embedding the message is dumped into the image with reference to a random generated key, based on this key the extraction of text is done from the image. So this method is a highly secured from eavesdropping and highly complex to identify the text data in the image and retrieving the text message from the message is also a resilient process. The extraction is only possible when the key is known. 

Sign in / Sign up

Export Citation Format

Share Document