Natural Language Processing Methods Research Articles

Enhancing the Identification of False News using Machine Learning Algorithms: A Comparative Study

In today's digital world filled with information overload, preventing the rampant spread of fake news has become an urgent task. Discover the Fake News Prediction System (FNPS), which uses advanced machine learning and technology to provide innovative solutions and powerful methodologies. Natural language processing methods. FNPS uses sophisticated feature engineering from diverse, curated datasets to identify underlying patterns in fraudulent content and significantly improves the ability to recognize authenticity. FNPS achieves outstanding performance using a combination of classifiers combining TF-IDF vectorization, deep learning architecture, and sentiment analysis, demonstrating its ability to accurately predict the legitimacy of news articles. Beyond simple forecasting, FNPS provides an intuitive user interface for evaluating news content in real time. This not only increases accessibility but also promotes media literacy and responsible consumption of information. Provides additional information and promotes robust public discourse. FNPS essentially demonstrates the revolutionary potential of advanced technology in ongoing combat. This will further the important public goal of ensuring the reliability and integrity of information in the digital age.

Using Natural Language Processing for a Computer-Aided Rapid Assessment of the Human Condition in Terms of Anorexia Nervosa

This paper demonstrates how natural language processing methods can support the computer-aided rapid assessment of young adults suffering from anorexia nervosa. We applied natural language processing and machine learning techniques to develop methods that classified body image notes into four categories (sick/healthy, past tense, irony, and sentiment) and analyzed personal vocabulary. The datasets consisted of notes from 115 anorexic patients, 85 healthy participants, and 50 participants with head and neck cancer. To evaluate the usefulness of the proposed approach, we interviewed ten professional psychologists who were experts in eating disorders, eight direct (first contact) staff, and fourteen school counselors and school psychologists. The developed tools correctly differentiated the individuals suffering from anorexia nervosa, which was reflected in the linguistic profile and the results of the machine learning classification of the body image notes. The developed tool also received a positive evaluation from the psychologists specializing in treating eating disorders, school psychologists, and nurses. The obtained results indicate the potential of using natural language processing techniques for the computer-aided rapid assessment of a person’s condition in terms of anorexia nervosa. This method could be applied as both a screening tool and for the regular monitoring of people at risk of eating disorders.

Big data application and corporate investment decisions: Evidence from A-share listed companies in China

Based on a natural language processing (NLP) method and annual reports from A-share listed companies in China from 2011 to 2020, this paper constructs a big data index for the corporate level and studies the impact of big data on corporate investment decisions. The study finds that big data significantly improves corporate investment decisions. From the perspective of index decomposition, data mining and mobile service are found to significantly improve corporate investment efficiency, while algorithm development and intelligent manufacturing mainly enhance the corporate investment level. The study also notes that heterogeneity may exist due to differences in financial, innovation, and legal environments. In terms of mechanisms, big data can positively influence corporate investment decisions by improving R&D investment and reducing transaction costs.

Regional Economic Sentiment: Constructing Quantitative Estimates from the Beige Book and Testing Their Ability to Forecast Recessions

We use natural language processing methods to quantify the sentiment expressed in the Federal Reserve's anecdotal summaries of current economic conditions in the national and 12 Federal Reserve District-level economies as published eight times per year in the Beige Book since 1970. We document that both national and District-level economic sentiment tend to rise and fall with the US business cycle. But economic sentiment is extremely heterogeneous across Districts, and we find that national economic sentiment is not always the simple aggregation of District-level sentiment. We show that the heterogeneity in District-level economic sentiment can be used, over and above the information contained in national economic sentiment, to better forecast US recessions.

Measuring interpersonal firearm violence: natural language processing methods to address limitations in criminal charge data.

Firearm violence constitutes a public health crisis in the United States, but comprehensive data infrastructure is lacking to study this problem. To address this challenge, we used natural language processing (NLP) to classify court record documents from alleged violent crimes as firearm-related or non-firearm-related. We accessed and digitized court records from the state of Washington (n = 1472). Human review established a gold standard label for firearm involvement (yes/no). We developed a key term search and trained supervised machine learning classifiers for this labeling task. Results were evaluated in a held-out test set. The decision tree performed best (F1 score: 0.82). The key term list had perfect recall (1.0) and a modest F1 score (0.65). This case report highlights the accuracy, feasibility, and potential time-saved by using NLP to identify firearm involvement in alleged violent crimes based on digitized narratives from court documents.

Sentiment Analysis on The Place of Interest in Malaysia

This study focuses on utilizing machine learning methods for sentiment analysis to identify positive and negative comments regarding Malaysian Places of Interest (PoI). The data was collected from Twitter using social media monitoring software and organized into tables. Pre-processing techniques and Natural Language Processing (NLP) methods were applied to handle missing values and prepare the text data for analysis. The dataset was then split into training and testing sets, and three supervised learning algorithms which are Support Vector Machine, Random Forest, and Naive Bayes were employed to evaluate the sentiment analysis models. The performance of each model was compared, and it was found that Support Vector Machine achieved the highest accuracy, recall score, F1 score, and precision score. This study demonstrates the potential to extend sentiment analysis to analyze sentiments expressed in texts written in the Malay language by utilizing the Malaya corpus. Additionally, visual dashboards can be created to present the findings and provide recommendations based on the insights gathered from the sentiment analysis of PoI feedback.

Technical Language Processing of Nuclear Power Plants Equipment Reliability Data

Operating nuclear power plants (NPPs) generate and collect large amounts of equipment reliability (ER) element data that contain information about the status of components, assets, and systems. Some of this information is in textual form where the occurrence of abnormal events or maintenance activities are described. Analyses of NPP textual data via natural language processing (NLP) methods have expanded in the last decade, and only recently the true potential of such analyses has emerged. So far, applications of NLP methods have been mostly limited to classification and prediction in order to identify the nature of the given textual element (e.g., safety or non-safety relevant). In this paper, we target a more complex problem: the automatic generation of knowledge based on a textual element in order to assist system engineers in assessing an asset’s historical health performance. The goal is to assist system engineers in the identification of anomalous behaviors, cause–effect relations between events, and their potential consequences, and to support decision-making such as the planning and scheduling of maintenance activities. “Knowledge extraction” is a very broad concept whose definition may vary depending on the application context. In our particular context, it refers to the process of examining an ER textual element to identify the systems or assets it mentions and the type of event it describes (e.g., component failure or maintenance activity). In addition, we wish to identify details such as measured quantities and temporal or cause–effect relations between events. This paper describes how ER textual data elements are first preprocessed to handle typos, acronyms, and abbreviations, then machine learning (ML) and rule-based algorithms are employed to identify physical entities (e.g., systems, assets, and components) and specific phenomena (e.g., failure or degradation). A few applications relevant from an NPP ER point of view are presented as well.

Exploring the connotation of “Local Community” in ICOMOS discourse: a textual analysis based on authoritative documents

As an authoritative institution in cultural heritage conservation, ICOMOS plays a crucial role in guiding local communities’ participation in heritage conservation. However, its scattered and vague descriptions of local communities pose significant obstacles to further research and practice of community participation in heritage conservation. Given the increasing importance of local communities in heritage conservation, it is essential to systematically explore the connotation of Local Community connotations within ICOMOS discourse. This research employs Natural Language Processing methods to analyze ICOMOS’s descriptions of Local Community. Utilizing computational techniques of word frequency calculation, LDA (Latent Dirichlet Allocation) topic model keyword calculation, and hierarchical clustering calculation, the research uncovers relevant keywords and its thematic clusters of Local Community. These findings are further elucidated by aligning them with the principles outlined in authoritative documents of ICOMOS. The research indicates that ICOMOS’s descriptions of Local Community can be summarized into four main keywords families. These keywords families can be summarized as a comprehensive Local Community “three-level, four-family” keywords system. The “Tourism” keywords family exhibits a close association with Local Community, highlighting ICOMOS’s heightened emphasis on heritage tourism. The “Management-Development” keywords family occupies the second level, emphasizing fundamental principles for local communities’ participation in heritage practices. The “Traditional-Knowledge” and “Social-Economic” Keywords Families, situated in the third level, respectively describe the value attributes and conservation approaches of local communities. Each keywords family formed over different periods, exhibiting varying trends of development. By systematically integrating ICOMOS’s descriptions of Local Community and employing Natural Language Processing for in-depth exploration, This research aims to construct a cognitive understanding of local communities from a new perspective of quantitative text analysis, with the intention of providing theoretical references for subsequent research on local communities.

Education hubs in Qatar and the United Arab Emirates: Analysis of discursive constructions using Latent Dirichlet Allocation

Advanced techniques for linguistic analysis provide the opportunity to extract meanings from the available documents on education hubs. We use Latent Dirichlet Allocation (LDA), a topic modelling method for natural language processing and big data mining, to analyze the discourse of education hubs in Qatar and the United Arab Emirates (UAE). Our data derive from a corpus of academic literature, non-peer-reviewed articles, and policy documents. The analysis shows that education hubs have been at the core of efforts to transition from a hydrocarbon-based economy to a knowledge economy. The analysis also shows that education hubs have been increasingly associated with the two countries’ efforts to achieve regional leadership in overlapping geopolitical spheres of influence. Describing the situation as a ‘constructive rivalry’, we highlight its geopolitical implications and we call attention to Knight, (2022) knowledge diplomacy whereby the two countries can use education hubs as a mechanism for exercising leadership in promoting peace and development in the broader region of the Middle East.c.

Classification-driven intelligent system for automated evaluation of higher education exam paper quality

AbstractEvaluating the quality of university exam papers is crucial for universities seeking institutional and program accreditation. Currently, exam papers are assessed manually, a process that can be tedious, lengthy, and in some cases, inconsistent. This is often due to the focus on assessing only the formal specifications of exam papers. This study develops an intelligent system for the automatic evaluation of university exam papers in terms of form and content, ensuring adherence to quality standards. The system is composed of two subsystems: the first evaluates compliance with formal specifications, and the second analyzes the content. The content analysis involves automatically categorizing exam questions based on Bloom's cognitive levels (BCLs) and determining the representation ratio of these levels in the exam paper. This subsystem comprises four main modules: 1) question collection, 2) text pre-processing using natural language processing (NLP) methods, 3) feature engineering using the CountVectorizer method to convert questions into feature vectors, and 4) a classification module based on the Logistic Regression (LR) algorithm to categorize exam questions into categories like knowledge, comprehension, application, analysis, synthesis, and evaluation. Experimental results indicate that the system achieves an average accuracy of 98.5%.

Automatic customer review summarization using deep learning-based hybrid sentiment analysis

Customer review summarization (CRS) offers business owners summarized customer feedback. The functionality of CRS mainly depends on the sentiment analysis (SA) model; hence it needs an efficient SA technique. The aim of this study is to construct an SA model employing deep learning for CRS (SADL-CRS) to present summarized data and assist businesses in understanding the behavior of their customers. The SA model employing deep learning (SADL) and CRS phases make up the proposed automatic SADL-CRS model. The SADL consists of review preprocessing, feature extraction, and sentiment classification. The preprocessing stage removes irrelevant text from the reviews using natural language processing (NLP) methods. The proposed hybrid approach combines review-related features and aspect-related features to efficiently extract the features and create a unique hybrid feature vector (HF) for each review. The classification of input reviews is performed using a deep learning (DL) classifier long short-term memory (LSTM). The CRS phase performs the automatic summarization employing the outcome of SADL. The experimental evaluation of the proposed model is done using diverse research data sets. The SADL-CRS model attains the average recall, precision, and F1-score of 95.53%, 95.76%, and 95.06%, respectively. The review summarization efficiency of the suggested model is improved by 6.12% compared to underlying CRS methods.

Research on Product Conceptual Design Scheme Configurations from a Designer–User Conflict Perspective

In the context of rapid product iteration, design conflicts arise from discrepancies in designers’ understanding of user needs, influenced by subjective preferences, behavioural stances, and other factors. This paper proposes a product conceptual design approach based on the design conflict perspective. First, user comments and design documents are collected. Natural language processing (NLP) methods, including cleaning, filtering, lexical segmentation, feature clustering, and sentiment analysis, are employed to identify design themes. The intuitionistic fuzzy sets (IFSs) and term frequency–inverse document frequency (TF-IDF) algorithms are then utilized to obtain evaluation matrices for the products from both users and designers. Subsequently, design conflicts between users and designers are calculated, and an optimal configuration for product conceptual design is determined through regression analysis and planning methods. Finally, the proposed method is validated using a mobile phone as a product example, and suggestions for product improvement are presented. The results indicate that considering design conflicts as a factor in product design and synthesizing designer and user product concepts enhance the accuracy and reliability of product conceptual design generation. The findings of this study offer new insights into the conceptual design configuration for product iteration.

Automatic categorization of self-acknowledged limitations in randomized controlled trial publications

Objective:Acknowledging study limitations in a scientific publication is a crucial element in scientific transparency and progress. However, limitation reporting is often inadequate. Natural language processing (NLP) methods could support automated reporting checks, improving research transparency. In this study, our objective was to develop a dataset and NLP methods to detect and categorize self-acknowledged limitations (e.g., sample size, blinding) reported in randomized controlled trial (RCT) publications. Methods:We created a data model of limitation types in RCT studies and annotated a corpus of 200 full-text RCT publications using this data model. We fine-tuned BERT-based sentence classification models to recognize the limitation sentences and their types. To address the small size of the annotated corpus, we experimented with data augmentation approaches, including Easy Data Augmentation (EDA) and Prompt-Based Data Augmentation (PromDA). We applied the best-performing model to a set of about 12K RCT publications to characterize self-acknowledged limitations at larger scale. Results:Our data model consists of 15 categories and 24 sub-categories (e.g., Population and its sub-category DiagnosticCriteria). We annotated 1090 instances of limitation types in 952 sentences (4.8 limitation sentences and 5.5 limitation types per article). A fine-tuned PubMedBERT model for limitation sentence classification improved upon our earlier model by about 1.5 absolute percentage points in F1 score (0.821 vs. 0.8) with statistical significance (p<.001). Our best-performing limitation type classification model, PubMedBERT fine-tuning with PromDA (Output View), achieved an F1 score of 0.7, improving upon the vanilla PubMedBERT model by 2.7 percentage points, with statistical significance (p<.001). Conclusion:The model could support automated screening tools which can be used by journals to draw the authors’ attention to reporting issues. Automatic extraction of limitations from RCT publications could benefit peer review and evidence synthesis, and support advanced methods to search and aggregate the evidence from the clinical trial literature.

Machine learning natural language processing for identifying venous thromboembolism: systematic review and meta-analysis

AbstractVenous thromboembolism (VTE) is a leading cause of preventable in-hospital mortality. Monitoring VTE cases is limited by the challenges of manual medical record review and diagnosis code interpretation. Natural language processing (NLP) can automate the process. Rule-based NLP methods are effective but time consuming. Machine learning (ML)-NLP methods present a promising solution. We conducted a systematic review and meta-analysis of studies published before May 2023 that use ML-NLP to identify VTE diagnoses in the electronic health records. Four reviewers screened all manuscripts, excluding studies that only used a rule-based method. A meta-analysis evaluated the pooled performance of each study’s best performing model that evaluated for pulmonary embolism and/or deep vein thrombosis. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with confidence interval (CI) were calculated by DerSimonian and Laird method using a random-effects model. Study quality was assessed using an adapted TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis) tool. Thirteen studies were included in the systematic review and 8 had data available for meta-analysis. Pooled sensitivity was 0.931 (95% CI, 0.881-0.962), specificity 0.984 (95% CI, 0.967-0.992), PPV 0.910 (95% CI, 0.865-0.941) and NPV 0.985 (95% CI, 0.977-0.990). All studies met at least 13 of the 21 NLP-modified TRIPOD items, demonstrating fair quality. The highest performing models used vectorization rather than bag-of-words and deep-learning techniques such as convolutional neural networks. There was significant heterogeneity in the studies, and only 4 validated their model on an external data set. Further standardization of ML studies can help progress this novel technology toward real-world implementation.

Performance analysis of three recommendation algorithms on Amazon datasets

Recommendation systems play a crucial role in enhancing user satisfaction and driving sales for businesses. They are essential in todays marketplaces, as they are able to suggest products and services that may interest a particular individual based on their past purchases. In this paper, empirical research is conducted on three distinct subsets of the Amazon dataset, namely Sports &amp; Outdoors, Movies &amp; TV, and Video Games, to comprehensively evaluate the performance of three distinct recommendation methods based on deep learning algorithms. These methods include the dot product method, (an updated version of the singular value decomposition algorithm), the neural network method, and the neural collaborative filtering model with natural language processing method. The results of this study reveal that deep learning-based recommendation systems can achieve more accurate results compared to traditional recommendation systems for three types of products. The implementation of these methods on Amazons dataset can help improve sales by correctly identifying customers interests and suggesting relevant items.

Building large-scale registries from unstructured clinical notes using a low-resource natural language processing pipeline

Building clinical registries is an important step in clinical research and improvement of patient care quality. Natural Language Processing (NLP) methods have shown promising results in extracting valuable information from unstructured clinical notes. However, the structure and nature of clinical notes are very different from regular text that state-of-the-art NLP models are trained and tested on, and they have their own set of challenges. In this study, we propose Sentence Extractor with Keywords (SE-K), an efficient and interpretable classification approach for extracting information from clinical notes and show that it outperforms more computationally expensive methods in text classification. Following the Institutional Review Board (IRB) approval, we used SE-K and two embedding based NLP approaches (Sentence Extractor with Embeddings (SE-E) and Bidirectional Encoder Representations from Transformers (BERT)) to develop comprehensive registry of anterior cruciate ligament surgeries from 20 years of unstructured clinical data at a multi-site tertiary-care regional children's hospital. The low-resource approach (SE-K) had better performance (average AUROC of 0.94 ± 0.04) than the embedding-based approaches (SE-E: 0.93 ± 0.04 and BERT: 0.87 ± 0.09) for out of sample validation, in addition to minimum performance drop between test and out-of-sample validation. Moreover, the SE-K approach was at least six times faster (on CPU) than SE-E (on CPU) and BERT (on GPU) and provides interpretability. Our proposed approach, SE-K, can be effectively used to extract relevant variables from clinic notes to build large-scale registries, with consistently better performance compared to the more resource-intensive approaches (e.g., BERT). Such approaches can facilitate information extraction from unstructured notes for registry building, quality improvement and adverse event monitoring.

Automated linguistic analysis in speech samples of Turkish-speaking patients with schizophrenia-spectrum disorders

Modern natural language processing (NLP) methods provide ways to objectively quantify language disturbances for potential use in diagnostic classification. We performed computerized language analysis in speech samples of 82 Turkish-speaking subjects, including 44 patients with schizophrenia spectrum disorders (SSD) and 38 healthy controls (HC). Exploratory analysis of speech samples involved 16 sentence-level semantic similarity features using SBERT (Sentence Bidirectional Encoder Representation from Text) as well as 8 generic and 8 part-of-speech (POS) features. The random forest classifier using SBERT-derived semantic similarity features achieved a mean accuracy of 85.6 % for the classification of SSD and HC. When semantic similarity features were combined with generic and POS features, the classifier's mean accuracy reached to 86.8 %. Our analysis reflected increased sentence-level semantic similarity scores in SSD. Generic and POS analyses revealed an increase in the use of verbs, proper nouns and pronouns in SSD while our results showed a decrease in the utilization of conjunctions, determiners, and both average and maximum sentence length in SSD compared to HC. Quantitative language features were correlated with the expressive deficit domain of BNSS (Brief Negative Symptom Scale) as well as with the duration of illness. These findings from Turkish-speaking interviews contribute to the growing evidence-based NLP-derived assessments in non-English-speaking patients.

Abstract 3779: Genomic and clinical characterization of metastatic patterns using real-word data from a large cohort of colorectal cancer patients

Abstract Background: Colorectal cancers (CRCs) can exhibit disparate metastatic patterns that affect outcomes. We investigated associations between genomic features and organ-specific metastatic tropism and we compared the frequency of actionable alterations detected in patients undergoing longitudinal clinical sequencing. Methods: We analyzed data for 6574 tumors from 6153 CRC patients, including 4510 primary and 2064 metastatic specimens. All patients had microsatellite stable (MSS) disease and were treated at Memorial Sloan Kettering. Paired primary and metastatic samples were available for 203 patients. Tumors were sequenced with MSK-IMPACT, a targeted DNA sequencing assay that identifies genomic alterations in 341-505 genes. Clinical annotations included sex, stage at diagnosis (Dx), and primary tumor location. History of metastatic disease was automatically retrieved from radiology reports using validated natural language processing methods; time to specific-site metastasis was modeled with Cox regression. False discovery rate (FDR) was used to correct for multiple hypothesis testing. The OncoKB knowledge base was used to identify clinically actionable alterations. Results: Liver (n=1068, 51.7%), peritoneal (n=269, 13.0%) and lung metastases (n=263, 12.7%) accounted for the majority of non-primary sequenced specimens. The frequency of actionable alterations (OncoKB Level≥3A) did not vary between unmatched metastatic and primary samples (12.3% vs 11.4%, p=0.302). In primary tumor samples from patients with localized disease at the time of diagnosis, TGFB pathway alterations were associated with increased risk of metastasis to the brain (HR=2.41, p=0.028), bone (HR=2.10, p&amp;lt;0.001), peritoneum (HR=1.82, p=0.001) and liver (HR=1.42, p=0.049). Alterations in the RAS pathway were associated with increased risk of lung (HR=1.47, p=0.009), peritoneum (HR=1.54, p=0.021) and liver (HR=1.44, p=0.026) metastases. By contrast, WNT pathway alterations were associated with a lower risk of developing lung (HR=0.69, p=0.033) and peritoneal metastasis (HR=0.68, p=0.081). Among patients with paired primary and metastatic samples, no significant difference was observed between the frequency of clinically actionable alterations in primary vs. metastatic specimens (16.7% vs. 18.2%, p=0.794). Presence of metastases-private or primary-private alterations did not correlate with site-specific metastasis risk. Conclusions: The risk of developing metastatic disease and organ-specific dissemination might be linked to genomic abnormalities detectable at the localized stage. No significant difference in the frequency of actionable alterations was observed between primary and metastatic CRC samples. Citation Format: Paolo Manca, Ayush V. Kris, Henry Walch, Christopher Fong, Justin Jee, Karl Pichotta, Nikolaus Schultz, Walid K. Chatila, Rona Yaeger, Francisco Sanchez-Vega. Genomic and clinical characterization of metastatic patterns using real-word data from a large cohort of colorectal cancer patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3779.

Development of automatic generation system for lung nodule finding descriptions.

Worldwide, lung cancer is the leading cause of cancer-related deaths. To manage lung nodules, radiologists observe computed tomography images, review various imaging findings, and record these in radiology reports. The report contents should be of high quality and uniform regardless of the radiologist. Here, we propose an artificial intelligence system that automatically generates descriptions related to lung nodules in computed tomography images. Our system consists of an image recognition method for extracting contents-namely, bronchopulmonary segments and nodule characteristics from images-and a natural language processing method to generate fluent descriptions. To verify our system's clinical usefulness, we conducted an experiment in which two radiologists created nodule descriptions of findings using our system. Through our system, the similarity of the described contents between the two radiologists (p = 0.001) and the comprehensiveness of the contents (p = 0.025) improved, while the accuracy did not significantly deteriorate (p = 0.484).

Improving Automated Labeling for ATT&amp;CK Tactics in Malware Threat Reports

Once novel malware is detected, threat reports are written by security companies that discover it. The reports often vary in the terminology describing the behavior of the malware making comparisons of reports of the same malware from different companies difficult. To aid in the automated discovery of novel malware, it was recently proposed that novel malware could be detected by identifying behaviors. This assumes that a core set of behaviors are present in most, if not all, malware variants. However, there is a lack of malware datasets that are labeled with behaviors. Motivated by a need to label malware with a common set of behaviors, this work examines automating the process of labeling malware with behaviors identified in malware threat reports despite the variability of terminology. To do so, we examine several techniques from the natural language processing (NLP) domain. We find that most state-of-the-art word embedding NLP methods require large amounts of data and are trained on generic corpora of text data—missing the nuances related to information security. To address this, we use simple feature selection techniques. We find that simple feature selection techniques generally outperform word embedding methods and achieve an increase of 6% in the F .5 -score over prior work when used to predict MITRE ATT&amp;CK tactics in threat reports. Our work indicates that feature selection, which has commonly been overlooked by sophisticated methods in NLP tasks, is beneficial for information security related tasks, where more sophisticated NLP methodologies are not able to pick out relevant information security terms.