Effective Technique to Reduce the Dimension of Text Data

In this article, features are selected using feature clustering and ranking of features for imbalanced text data. Initially the text documents are represented in lower dimension using the term class relevance (TCR) method. The class wise clustering is recommended to balance the documents in each class. Subsequently, the clusters are treated as classes and the documents of each cluster are represented in the lower dimensional form using the TCR again. The features are clustered and for each feature cluster the cluster representative is selected and these representatives are used as selected features of the documents. Hence, this proposed model reduces the dimension to a smaller number of features. For selecting the cluster representative, four feature evaluation methods are used and classification is done by using SVM classifier. The performance of the method is compared with the global feature ranking method. The experiment is conducted on two benchmark datasets the Reuters-21578 and the TDT2 dataset. The experimental results show that this method performs well when compared to the other existing works.

Download Full-text

Classification and pattern extraction of incidents: a deep learning-based approach

Neural Computing and Applications ◽

10.1007/s00521-021-06780-3 ◽

2022 ◽

Author(s):

Sobhan Sarkar ◽

Sammangi Vinay ◽

Chawki Djeddi ◽

J. Maiti

Keyword(s):

Superior Performance ◽

Hidden Information ◽

Text Data ◽

Moment Estimation ◽

The Arts ◽

Proposed Model ◽

Benchmark Datasets ◽

Unexplored Area ◽

Key Terms

AbstractClassifying or predicting occupational incidents using both structured and unstructured (text) data are an unexplored area of research. Unstructured texts, i.e., incident narratives are often unutilized or underutilized. Besides the explicit information, there exist a large amount of hidden information present in a dataset, which cannot be explored by the traditional machine learning (ML) algorithms. There is a scarcity of studies that reveal the use of deep neural networks (DNNs) in the domain of incident prediction, and its parameter optimization for achieving better prediction power. To address these issues, initially, key terms are extracted from the unstructured texts using LDA-based topic modeling. Then, these key terms are added with the predictor categories to form the feature vector, which is further processed for noise reduction and fed to the adaptive moment estimation (ADAM)-based DNN (i.e., ADNN) for classification, as ADAM is superior to GD, SGD, and RMSProp. To evaluate the effectiveness of our proposed method, a comparative study has been conducted using some state-of-the-arts on five benchmark datasets. Moreover, a case study of an integrated steel plant in India has been demonstrated for the validation of the proposed model. Experimental results reveal that ADNN produces superior performance than others in terms of accuracy. Therefore, the present study offers a robust methodological guide that enables us to handle the issues of unstructured data and hidden information for developing a predictive model.

Download Full-text

A Densely Connected GRU Neural Network Based on Coattention Mechanism for Chinese Rice-Related Question Similarity Matching

Agronomy ◽

10.3390/agronomy11071307 ◽

2021 ◽

Vol 11 (7) ◽

pp. 1307

Author(s):

Haoriqin Wang ◽

Huaji Zhu ◽

Huarui Wu ◽

Xiaomin Wang ◽

Xiao Han ◽

...

Keyword(s):

The Evaluation of Accuracy Performance in an Enhanced Embedded Feature Selection for Unstructured Text Classification

Iraqi Journal of Science ◽

10.24996/ijs.2020.61.12.28 ◽

2020 ◽

pp. 3397-3407

Author(s):

Nur Syafiqah Mohd Nafis ◽

Suryanti Awang

Keyword(s):

Feature Selection ◽

Text Classification ◽

Training Dataset ◽

Recursive Feature Elimination ◽

High Dimensional ◽

Significant Feature ◽

Support Vector ◽

Svm Classifier ◽

Text Documents ◽

Text Document

Text documents are unstructured and high dimensional. Effective feature selection is required to select the most important and significant feature from the sparse feature space. Thus, this paper proposed an embedded feature selection technique based on Term Frequency-Inverse Document Frequency (TF-IDF) and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) for unstructured and high dimensional text classificationhis technique has the ability to measure the feature’s importance in a high-dimensional text document. In addition, it aims to increase the efficiency of the feature selection. Hence, obtaining a promising text classification accuracy. TF-IDF act as a filter approach which measures features importance of the text documents at the first stage. SVM-RFE utilized a backward feature elimination scheme to recursively remove insignificant features from the filtered feature subsets at the second stage. This research executes sets of experiments using a text document retrieved from a benchmark repository comprising a collection of Twitter posts. Pre-processing processes are applied to extract relevant features. After that, the pre-processed features are divided into training and testing datasets. Next, feature selection is implemented on the training dataset by calculating the TF-IDF score for each feature. SVM-RFE is applied for feature ranking as the next feature selection step. Only top-rank features will be selected for text classification using the SVM classifier. Based on the experiments, it shows that the proposed technique able to achieve 98% accuracy that outperformed other existing techniques. In conclusion, the proposed technique able to select the significant features in the unstructured and high dimensional text document.

Download Full-text

Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6284 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7797-7804

Author(s):

Goran Glavašš ◽

Swapna Somasundaran

Keyword(s):

State Of The Art ◽

Language Transfer ◽

Text Segmentation ◽

Word Embeddings ◽

Neural Architecture ◽

Text Coherence ◽

Sentence Level ◽

Proposed Model ◽

Benchmark Datasets ◽

Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

Download Full-text

Assessment of Twitter Data Clusters with Cosine-Based Validation Metrics Using Hybrid Topic Models

Ingénierie des systèmes d information ◽

10.18280/isi.250606 ◽

2020 ◽

Vol 25 (6) ◽

pp. 755-769

Author(s):

Noorullah R. Mohammed ◽

Moulana Mohammed

Keyword(s):

Data Clustering ◽

Topic Models ◽

Cluster Validity ◽

Text Documents ◽

Text Data ◽

Validity Assessment ◽

Text Document ◽

Cluster Validity Indices ◽

Validity Indices ◽

Data Clusters

Text data clustering is performed for organizing the set of text documents into the desired number of coherent and meaningful sub-clusters. Modeling the text documents in terms of topics derivations is a vital task in text data clustering. Each tweet is considered as a text document, and various topic models perform modeling of tweets. In existing topic models, the clustering tendency of tweets is assessed initially based on Euclidean dissimilarity features. Cosine metric is more suitable for more informative assessment, especially of text clustering. Thus, this paper develops a novel cosine based external and interval validity assessment of cluster tendency for improving the computational efficiency of tweets data clustering. In the experimental, tweets data clustering results are evaluated using cluster validity indices measures. Experimentally proved that cosine based internal and external validity metrics outperforms the other using benchmarked and Twitter-based datasets.

Download Full-text

The Classification System of Literary Works Based on K-Means Clustering

Journal of Interconnection Networks ◽

10.1142/s0219265921410012 ◽

2021 ◽

pp. 2141001

Author(s):

Sanqiang Wei ◽

Hongxia Hou ◽

Hua Sun ◽

Wei Li ◽

Wenxia Song

Keyword(s):

Clustering Algorithm ◽

Performance Ratio ◽

Levels Of Abstraction ◽

Text Documents ◽

Text Data ◽

Literary Works ◽

Accuracy Comparison ◽

Word Classification ◽

Text Features ◽

And Performance

The plots in certain literary works are very complicated and hinder readers from understanding them. Therefore tools should be proposed to support readers; comprehension of complex literary works supports their understanding by providing the most important information to readers. A human reader must capture multiple levels of abstraction and meaning to formulate an understanding of a document. Hence, in this paper, an Improved [Formula: see text]-means clustering algorithm (IKCA) has been proposed for literary word classification. For text data, the words that can express exact semantic in a class are generally better features. This paper uses the proposed technique to capture numerous cluster centroids for every class and then select the high-frequency words in centroids the text features for classification. Furthermore, neural networks have been used to classify text documents and [Formula: see text]-mean to cluster text documents. To develop the model based on unsupervised and supervised techniques to meet and identify the similarity between documents. The numerical results show that the suggested model will enhance to increases quality comparison of the existing Algorithm and [Formula: see text]-means algorithm, accuracy comparison of ALA and IKCA (95.2%), time is taken for clustering is less than 2 hours, success rate (97.4%) and performance ratio (98.1%).

Download Full-text

Detection of Botnet Based Attacks on Network

Handbook of Research on Network Forensics and Analysis Techniques - Advances in Information Security, Privacy, and Ethics ◽

10.4018/978-1-5225-4100-4.ch007 ◽

2018 ◽

pp. 101-116

Author(s):

Prachi

Keyword(s):

Large Scale ◽

Flow Analysis ◽

Traffic Analysis ◽

High Accuracy ◽

Machine Learning Techniques ◽

Botnet Detection ◽

Learning Techniques ◽

Proposed Model ◽

Benchmark Datasets ◽

Traffic Flow Analysis

This chapter describes how with Botnets becoming more and more the leading cyber threat on the web nowadays, they also serve as the key platform for carrying out large-scale distributed attacks. Although a substantial amount of research in the fields of botnet detection and analysis, bot-masters inculcate new techniques to make them more sophisticated, destructive and hard to detect with the help of code encryption and obfuscation. This chapter proposes a new model to detect botnet behavior on the basis of traffic analysis and machine learning techniques. Traffic analysis behavior does not depend upon payload analysis so the proposed technique is immune to code encryption and other evasion techniques generally used by bot-masters. This chapter analyzes the benchmark datasets as well as real-time generated traffic to determine the feasibility of botnet detection using traffic flow analysis. Experimental results clearly indicate that a proposed model is able to classify the network traffic as a botnet or as normal traffic with a high accuracy and low false-positive rates.

Download Full-text

Incorporating Text OLAP in Business Intelligence

Business Intelligence Applications and the Web - Advances in Business Information Systems and Analytics ◽

10.4018/978-1-61350-038-5.ch004 ◽

2011 ◽

pp. 77-101 ◽

Cited By ~ 1

Author(s):

Byung-Kwon Park ◽

Il-Yeol Song

Keyword(s):

Information Retrieval ◽

Text Mining ◽

Business Intelligence ◽

Multidimensional Analysis ◽

Web Pages ◽

Data Types ◽

Text Documents ◽

Text Data ◽

Platform Architecture ◽

Unstructured Text

As the amount of data grows very fast inside and outside of an enterprise, it is getting important to seamlessly analyze both data types for total business intelligence. The data can be classified into two categories: structured and unstructured. For getting total business intelligence, it is important to seamlessly analyze both of them. Especially, as most of business data are unstructured text documents, including the Web pages in Internet, we need a Text OLAP solution to perform multidimensional analysis of text documents in the same way as structured relational data. We first survey the representative works selected for demonstrating how the technologies of text mining and information retrieval can be applied for multidimensional analysis of text documents, because they are major technologies handling text data. And then, we survey the representative works selected for demonstrating how we can associate and consolidate both unstructured text documents and structured relation data for obtaining total business intelligence. Finally, we present a future business intelligence platform architecture as well as related research topics. We expect the proposed total heterogeneous business intelligence architecture, which integrates information retrieval, text mining, and information extraction technologies all together, including relational OLAP technologies, would make a better platform toward total business intelligence.

Download Full-text

Automatic Keyword Extraction From Text Documents

Digital Technology Advancements in Knowledge Management - Advances in Knowledge Acquisition, Transfer, and Management ◽

10.4018/978-1-7998-6792-0.ch004 ◽

2021 ◽

pp. 71-91

Author(s):

Furkan Goz ◽

Alev Mutlu

Keyword(s):

Information Retrieval ◽

State Of The Art ◽

Online News ◽

Evaluation Metrics ◽

Keyword Extraction ◽

Feature Engineering ◽

Extraction Techniques ◽

Text Documents ◽

Scientific Papers ◽

Benchmark Datasets

Keyword indexing is the problem of assigning keywords to text documents. It is an important task as keywords play crucial roles in several information retrieval tasks. The problem is also challenging as the number of text documents is increasing, and such documents come in different forms (i.e., scientific papers, online news articles, and microblog posts). This chapter provides an overview of keyword indexing and elaborates on keyword extraction techniques. The authors provide the general motivations behind the supervised and the unsupervised keyword extraction and enumerate several pioneering and state-of-the-art techniques. Feature engineering, evaluation metrics, and benchmark datasets used to evaluate the performance of keyword extraction systems are also discussed.

Download Full-text

Matching with Text Data: An Experimental Evaluation of Methods for Matching Documents and of Measuring Match Quality

Political Analysis ◽

10.1017/pan.2020.1 ◽

2020 ◽

Vol 28 (4) ◽

pp. 445-468 ◽

Cited By ~ 3

Author(s):

Reagan Mozer ◽

Luke Miratrix ◽

Aaron Russell Kaufman ◽

L. Jason Anastasopoulos

Keyword(s):

Propensity Scores ◽

Human Subjects ◽

Medical Intervention ◽

Exact Matching ◽

Match Quality ◽

Text Documents ◽

Text Data ◽

News Sources ◽

Text Matching

Matching for causal inference is a well-studied problem, but standard methods fail when the units to match are text documents: the high-dimensional and rich nature of the data renders exact matching infeasible, causes propensity scores to produce incomparable matches, and makes assessing match quality difficult. In this paper, we characterize a framework for matching text documents that decomposes existing methods into (1) the choice of text representation and (2) the choice of distance metric. We investigate how different choices within this framework affect both the quantity and quality of matches identified through a systematic multifactor evaluation experiment using human subjects. Altogether, we evaluate over 100 unique text-matching methods along with 5 comparison methods taken from the literature. Our experimental results identify methods that generate matches with higher subjective match quality than current state-of-the-art techniques. We enhance the precision of these results by developing a predictive model to estimate the match quality of pairs of text documents as a function of our various distance scores. This model, which we find successfully mimics human judgment, also allows for approximate and unsupervised evaluation of new procedures in our context. We then employ the identified best method to illustrate the utility of text matching in two applications. First, we engage with a substantive debate in the study of media bias by using text matching to control for topic selection when comparing news articles from thirteen news sources. We then show how conditioning on text data leads to more precise causal inferences in an observational study examining the effects of a medical intervention.

Download Full-text