DOCSLIB.ORG

Biomedical Natural Language Processing and Text Mining

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Biomedical Natural Language Processing and Text Mining To protect the rights of the author(s) and publisher we inform you that this PDF is an uncorrected proof for internal business use only by the author(s), editor(s), reviewer(s), Elsevier and typesetter SPS. It is not allowed to publish this proof online or in print. This proof copy is the copyright property of the publisher and is confidential until formal publication. B978-0-12-401678-1.00006-3 00006 AUTHOR QUERY FORM Book: Methods in Biomedical Please e-mail your responses and any Informatics corrections to: Chapter: 6 E-mail: [email protected] Dear Author, Any queries or remarks that have arisen during the processing of your manuscript are listed below and are highlighted by flags in the proof. (AU indicates author queries; ED indicates editor queries; and TS/TY indicates typesetter queries.) Please check your proof carefully and answer all AU queries. Mark all corrections and query answers at the appropriate place in the proof (e.g., by using on-screen annotation in the PDF file http://www.elsevier.com/framework_authors/tutorials/ePDF_voice_skin.swf) or compile them in a separate list, and tick off below to indicate that you have answered the query. Please return your input as instructed by the project manager. Uncited references: References that occur in the reference list but are not cited in the text. Please position each reference in the text or delete it from the reference list. Missing references: References listed below were noted in the text but are missing from the reference list. Please make the reference list complete or remove the references from the text. Location in Chapter Query / remark AU:1, page 33 This section comprises references that occur in the reference list but not in the body of the text. Please position each ref- erence in the text or, alternatively, delete it. Any reference not dealt with will be retained in this section. AU:2, page 1 The country name has been inserted for the author affiliation. Please check, and correct if necessary. AU:3, page 34 Please provide author name for Ref. [1]. AU:4, page 34 Please provide volume number for Ref. [3,6,24,49,50]. AU:5, page 36 Please note that the deletion of term U% in Ref. [42]. AU:6, page 36 Please check the year in Ref. [50]. Cohen 978-0-12-401678-1 To protect the rights of the author(s) and publisher we inform you that this PDF is an uncorrected proof for internal business use only by the author(s), editor(s), reviewer(s), Elsevier and typesetter SPS. It is not allowed to publish this proof online or in print. This proof copy is the copyright property of the publisher and is confidential until formal publication. Chapter 6 Biomedical Natural Language Processing and Text Mining Kevin Bretonnel Cohen Computational Bioscience Program, University of Colorado School of Medicine, Department of Linguistics, University of Colorado at Boulder, USA AQ2 CHAPTER OUTLINE 6.1 Natural Language Processing and Text Mining Defined 2 6.2 Natural Language 2 6.3 Approaches to Natural Language Processing and Text Mining 4 6.4 Some Special Considerations of Natural Language Processing in the Biomedical Domain 5 6.5 Building Blocks of Natural Language Processing Applications 8 6.5.1 Document Segmentation 9 6.5.2 Sentence Segmentation 10 6.5.3 Tokenization 10 6.5.4 Part of Speech Tagging 11 6.5.5 Parsing 11 6.6 Additional Components of Natural Language Processing Applications 12 6.6.1 Word Sense Disambiguation 12 6.6.2 Negation Detection 12 6.6.3 Temporality 13 6.6.4 Context Determination 13 6.6.5 Hedging 14 6.7 Evaluation in Natural Language Processing 15 6.8 Practical Applications: Text Mining Tasks 17 6.8.1 Information Retrieval 17 6.8.2 Named Entity Recognition 18 6.8.3 Named Entity Normalization 19 6.8.4 Information Extraction 21 6.8.5 Summarization 25 6.8.6 Cohort Retrieval and Phenotype Definition 26 6.9 Software Engineering in Natural Language Processing 28 6.9.1 Architectures 28 Methods in Biomedical Informatics. http://dx.doi.org/10.1016/B978-0-12-401678-1.00006-3 © 2014 Elsevier Inc. All rights reserved. 1 Cohen 978-0-12-401678-1 To protect the rights of the author(s) and publisher we inform you that this PDF is an uncorrected proof for internal business use only by the author(s), editor(s), reviewer(s), Elsevier and typesetter SPS. It is not allowed to publish this proof online or in print. This proof copy is the copyright property of the publisher and is confidential until formal publication. B978-0-12-401678-1.00006-3 00006 2 CHAPTER 6 Biomedical Natural Language Processing and Text Mining 6.9.2 Scaling 30 6.9.3 Quality Assurance and Testing 31 6.10 Conclusion 34 Acknowledgments 34 References 34 s0005 6.1 NATURAL LANGUAGE PROCESSING AND TEXT MINING DEFINED p0005 Natural language processing is the study of computer programs that take natural, or human, language as input. Natural language processing appli- cations may approach tasks ranging from low-level processing, such as assigning parts of speech to words, to high-level tasks, such as answering questions. Text mining is the use of natural language processing for practi- cal tasks, often related to finding information in prose of various kinds. In practice, natural language processing and text mining exist on a continuum, and there is no hard and fast line between the two. s0010 6.2 NATURAL LANGUAGE p0010 Natural language is human language, as opposed to computer languages. The difference between them lies in the presence of ambiguity. No well- designed computer language is ambiguous. In contrast, all known natural languages exhibit the property of ambiguity. Ambiguity occurs when an input can have more than one interpretation. Ambiguity exists at all lev- els of human language. (For illustrative purposes, we will focus on written language, since that is the domain of most biomedical natural language pro- cessing, with the exception of speech recognition applications.) Consider, for example, the word discharge. This word is ambiguous in that it may be a noun or a verb. In this example, we see both cases: With a decreased LOS, inpatient rehabilitation services will have to improve FIM efficiency or discharge patients with lower discharge FIM scores. (PMID 12917856) p0015 In the case of discharge patients, it is a verb. In the case of discharge FIM scores, it is a noun. Suppose that an application (called a part of speech tag- ger) has determined that it is a noun. It remains ambiguous as to its meaning. In these examples, we see two common meanings in biomedical text: Patient was prescribed codeine upon discharge The discharge was yellow and purulent p0020 In the first case, discharge has the meaning “release from the hospital,” while in the second case, it refers to a body fluid. Once an application Cohen 978-0-12-401678-1 To protect the rights of the author(s) and publisher we inform you that this PDF is an uncorrected proof for internal business use only by the author(s), editor(s), reviewer(s), Elsevier and typesetter SPS. It is not allowed to publish this proof online or in print. This proof copy is the copyright property of the publisher and is confidential until formal publication. B978-0-12-401678-1.00006-3 00006 6.2 Natural Language 3 has determined which is the correct meaning, it remains ambiguous as to its relationship to the words with which it appears—i.e., there is syntac- tic ambiguity. Should discharge FIM scores be interpreted as discharge modifying FIM scores, or as discharge FIM modifying scores? The correct analyses—noun versus verb, release from hospital versus body fluid, and discharge [FIM scores] versus [discharge FIM] scores—are so obvious to the human reader that we are typically not even consciously aware of the ambiguities. However, ambiguity is so pervasive in natural language that it is difficult to produce a sentence that is not ambiguous in some way, and the ambiguity that humans resolve so easily is one of the central problems that natural language processing must deal with. p0025 The statistical properties of language would be much different if the same ideas were always presented the same way. However, one of the predomi- nant features of human language is that it allows for an enormous amount of variability. Just as we saw that ambiguity is a fact at all levels of language, variability occurs at all levels of language as well. p0030 On the most basic level, corresponding to the sounds of spoken language, we have variability in spelling. This is most noticeable when compar- ing British and American medical English, where we see frequent vari- ants like haematoma in British English versus hematoma in American English. p0035 At the level of morphemes, or word parts, we see ambiguity in how words should be analyzed. Given a word such as unlockable (PMID 23003012), should we interpret it as [un[lockable]] (not capable of being locked), or as [[unlock]able] (capable of being unlocked)? p0040 At the level of words, the phenomenon of synonymy allows for using different, but (roughly) equivalent, words. For example, we might see cardiac surgery referred to as heart surgery. One common type of synonymy comes from using abbreviations or acronyms, such as CAT for computed axial tomography. Of course, synonymy multiplies the chances for ambiguity—it is commonly the case that biomedical synonyms can have multiple definitions. p0045 Variability exists at the syntactic level, as well.
Load more

Recommended publications
  • Information Retrieval Application of Text Mining Also on Bio-Medical Fields
    JOURNAL OF CRITICAL REVIEWS ISSN- 2394-5125 VOL 7, ISSUE 8, 2020 INFORMATION RETRIEVAL APPLICATION OF TEXT MINING ALSO ON BIO-MEDICAL FIELDS Charan Singh Tejavath1, Dr. Tryambak Hirwarkar2 1Research Scholar, Dept. of Computer Science & Engineering, Sri Satya Sai University of Technology & Medical Sciences, Sehore, Bhopal-Indore Road, Madhya Pradesh, India. 2Research Guide, Dept. of Computer Science & Engineering, Sri Satya Sai University of Technology & Medical Sciences, Sehore, Bhopal Indore Road, Madhya Pradesh, India. Received: 11.03.2020 Revised: 21.04.2020 Accepted: 27.05.2020 ABTRACT: Electronic clinical records contain data on all parts of health care. Healthcare data frameworks that gather a lot of textual and numeric data about patients, visits, medicines, doctor notes, and so forth. The electronic archives encapsulate data that could prompt an improvement in health care quality, advancement of clinical and exploration activities, decrease in clinical mistakes, and decrease in healthcare costs. In any case, the reports that contain the health record are wide-going in multifaceted nature, length, and utilization of specialized jargon, making information revelation complex. The ongoing accessibility of business text mining devices gives a one of a kind chance to remove basic data from textual information files. This paper portrays the biomedical text-mining technology. KEYWORDS: Text-mining technology, Bio-medical fields, Textual information files. © 2020 by Advance Scientific Research. This is an open-access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/) DOI: http://dx.doi.org/10.31838/jcr.07.08.357 I. INTRODUCTION The corpus of biomedical data is becoming quickly. New and helpful outcomes show up each day in research distributions, from diary articles to book parts to workshop and gathering procedures.
    [Show full text]
  • Barriers to Retrieving Patient Information from Electronic Health Record Data: Failure Analysis from the TREC Medical Records Track
    Barriers to Retrieving Patient Information from Electronic Health Record Data: Failure Analysis from the TREC Medical Records Track Tracy Edinger, ND, Aaron M. Cohen, MD, MS, Steven Bedrick, PhD, Kyle Ambert, BA, William Hersh, MD Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR, USA Abstract Objective: Secondary use of electronic health record (EHR) data relies on the ability to retrieve accurate and complete information about desired patient populations. The Text Retrieval Conference (TREC) 2011 Medical Records Track was a challenge evaluation allowing comparison of systems and algorithms to retrieve patients eligible for clinical studies from a corpus of de-identified medical records, grouped by patient visit. Participants retrieved cohorts of patients relevant to 35 different clinical topics, and visits were judged for relevance to each topic. This study identified the most common barriers to identifying specific clinic populations in the test collection. Methods: Using the runs from track participants and judged visits, we analyzed the five non-relevant visits most often retrieved and the five relevant visits most often overlooked. Categories were developed iteratively to group the reasons for incorrect retrieval for each of the 35 topics. Results: Reasons fell into nine categories for non-relevant visits and five categories for relevant visits. Non-relevant visits were most often retrieved because they contained a non-relevant reference to the topic terms. Relevant visits were most often infrequently retrieved because they used a synonym for a topic term. Conclusions : This failure analysis provides insight into areas for future improvement in EHR-based retrieval with techniques such as more widespread and complete use of standardized terminology in retrieval and data entry systems.
    [Show full text]
  • Text Mining Course for KNIME Analytics Platform
    Text Mining Course for KNIME Analytics Platform KNIME AG Copyright © 2018 KNIME AG Table of Contents 1. The Open Analytics Platform 2. The Text Processing Extension 3. Importing Text 4. Enrichment 5. Preprocessing 6. Transformation 7. Classification 8. Visualization 9. Clustering 10. Supplementary Workflows Licensed under a Creative Commons Attribution- ® Copyright © 2018 KNIME AG 2 Noncommercial-Share Alike license 1 https://creativecommons.org/licenses/by-nc-sa/4.0/ Overview KNIME Analytics Platform Licensed under a Creative Commons Attribution- ® Copyright © 2018 KNIME AG 3 Noncommercial-Share Alike license 1 https://creativecommons.org/licenses/by-nc-sa/4.0/ What is KNIME Analytics Platform? • A tool for data analysis, manipulation, visualization, and reporting • Based on the graphical programming paradigm • Provides a diverse array of extensions: • Text Mining • Network Mining • Cheminformatics • Many integrations, such as Java, R, Python, Weka, H2O, etc. Licensed under a Creative Commons Attribution- ® Copyright © 2018 KNIME AG 4 Noncommercial-Share Alike license 2 https://creativecommons.org/licenses/by-nc-sa/4.0/ Visual KNIME Workflows NODES perform tasks on data Not Configured Configured Outputs Inputs Executed Status Error Nodes are combined to create WORKFLOWS Licensed under a Creative Commons Attribution- ® Copyright © 2018 KNIME AG 5 Noncommercial-Share Alike license 3 https://creativecommons.org/licenses/by-nc-sa/4.0/ Data Access • Databases • MySQL, MS SQL Server, PostgreSQL • any JDBC (Oracle, DB2, …) • Files • CSV, txt
    [Show full text]
  • Biomedical Text Mining: a Survey of Recent Progress
    Chapter 14 BIOMEDICAL TEXT MINING: A SURVEY OF RECENT PROGRESS Matthew S. Simpson Lister Hill National Center for Biomedical Communications United States National Library of Medicine, National Institutes of Health [email protected] Dina Demner-Fushman Lister Hill National Center for Biomedical Communications United States National Library of Medicine, National Institutes of Health [email protected] Abstract The biomedical community makes extensive use of text mining tech- nology. In the past several years, enormous progress has been made in developing tools and methods, and the community has been witness to some exciting developments. Although the state of the community is regularly reviewed, the sheer volume of work related to biomedical text mining and the rapid pace in which progress continues to be made make this a worthwhile, if not necessary, endeavor. This chapter pro- vides a brief overview of the current state of text mining in the biomed- ical domain. Emphasis is placed on the resources and tools available to biomedical researchers and practitioners, as well as the major text mining tasks of interest to the community. These tasks include the recognition of explicit facts from biomedical literature, the discovery of previously unknown or implicit facts, document summarization, and question answering. For each topic, its basic challenges and methods are outlined and recent and influential work is reviewed. Keywords: Biomedical information extraction, named entity recognition, relations, events, summarization, question answering, literature-based discovery C.C. Aggarwal and C.X. Zhai (eds.), Mining Text Data, DOI 10.1007/978-1-4614-3223-4_14, 465 © Springer Science+Business Media, LLC 2012 466 MINING TEXT DATA 1.
    [Show full text]
  • Application of Machine Learning in Automatic Sentiment Recognition from Human Speech
    Application of Machine Learning in Automatic Sentiment Recognition from Human Speech Zhang Liu Ng EYK Anglo-Chinese Junior College College of Engineering Singapore Nanyang Technological University (NTU) Singapore [email protected] Abstract— Opinions and sentiments are central to almost all human human activities and have a wide range of applications. As activities and have a wide range of applications. As many decision many decision makers turn to social media due to large makers turn to social media due to large volume of opinion data volume of opinion data available, efficient and accurate available, efficient and accurate sentiment analysis is necessary to sentiment analysis is necessary to extract those data. Business extract those data. Hence, text sentiment analysis has recently organisations in different sectors use social media to find out become a popular field and has attracted many researchers. However, consumer opinions to improve their products and services. extracting sentiments from audio speech remains a challenge. This project explores the possibility of applying supervised Machine Political party leaders need to know the current public Learning in recognising sentiments in English utterances on a sentiment to come up with campaign strategies. Government sentence level. In addition, the project also aims to examine the effect agencies also monitor citizens’ opinions on social media. of combining acoustic and linguistic features on classification Police agencies, for example, detect criminal intents and cyber accuracy. Six audio tracks are randomly selected to be training data threats by analysing sentiment valence in social media posts. from 40 YouTube videos (monologue) with strong presence of In addition, sentiment information can be used to make sentiments.
    [Show full text]
  • Text KM & Text Mining
    Text KM & Text Mining An Introduction to Managing Knowledge in Unstructured Natural Language Documents Dekai Wu HKUST Human Language Technology Center Department of Computer Science and Engineering University of Science and Technology Hong Kong http://www.cs.ust.hk/~dekai © 2008 Dekai Wu Lecture Objectives Introduction to the concept of Text KM and Text Mining (TM) How to exploit knowledge encoded in text form How text mining is different from data mining Introduction to the various aspects of Natural Language Processing (NLP) Introduction to the different tools and methods available for TM HKUST Human Language Technology Center © 2008 Dekai Wu Textual Knowledge Management Text KM oversees the storage, capturing and sharing of knowledge encoded in unstructured natural language documents 80-90% of an organization’s explicit knowledge resides in plain English (Chinese, Japanese, Spanish, …) documents – not in structured relational databases! Case libraries are much more reasonably stored as natural language documents, than encoded into relational databases Most knowledge encoded as text will never pass through explicit KM processes (eg, email) HKUST Human Language Technology Center © 2008 Dekai Wu Text Mining Text Mining analyzes unstructured natural language documents to extract targeted types of knowledge Extracts knowledge that can then be inserted into databases, thereby facilitating structured data mining techniques Provides a more natural user interface for entering knowledge, for both employees and developers Reduces
    [Show full text]
  • Knowledge-Powered Deep Learning for Word Embedding
    Knowledge-Powered Deep Learning for Word Embedding Jiang Bian, Bin Gao, and Tie-Yan Liu Microsoft Research {jibian,bingao,tyliu}@microsoft.com Abstract. The basis of applying deep learning to solve natural language process- ing tasks is to obtain high-quality distributed representations of words, i.e., word embeddings, from large amounts of text data. However, text itself usually con- tains incomplete and ambiguous information, which makes necessity to leverage extra knowledge to understand it. Fortunately, text itself already contains well- defined morphological and syntactic knowledge; moreover, the large amount of texts on the Web enable the extraction of plenty of semantic knowledge. There- fore, it makes sense to design novel deep learning algorithms and systems in order to leverage the above knowledge to compute more effective word embed- dings. In this paper, we conduct an empirical study on the capacity of leveraging morphological, syntactic, and semantic knowledge to achieve high-quality word embeddings. Our study explores these types of knowledge to define new basis for word representation, provide additional input information, and serve as auxiliary supervision in deep learning, respectively. Experiments on an analogical reason- ing task, a word similarity task, and a word completion task have all demonstrated that knowledge-powered deep learning can enhance the effectiveness of word em- bedding. 1 Introduction With rapid development of deep learning techniques in recent years, it has drawn in- creasing attention to train complex and deep models on large amounts of data, in order to solve a wide range of text mining and natural language processing (NLP) tasks [4, 1, 8, 13, 19, 20].
    [Show full text]
  • 1 Application of Text Mining to Biomedical Knowledge Extraction: Analyzing Clinical Narratives and Medical Literature
    Amy Neustein, S. Sagar Imambi, Mário Rodrigues, António Teixeira and Liliana Ferreira 1 Application of text mining to biomedical knowledge extraction: analyzing clinical narratives and medical literature Abstract: One of the tools that can aid researchers and clinicians in coping with the surfeit of biomedical information is text mining. In this chapter, we explore how text mining is used to perform biomedical knowledge extraction. By describing its main phases, we show how text mining can be used to obtain relevant information from vast online databases of health science literature and patients’ electronic health records. In so doing, we describe the workings of the four phases of biomedical knowledge extraction using text mining (text gathering, text preprocessing, text analysis, and presentation) entailed in retrieval of the sought information with a high accuracy rate. The chapter also includes an in depth analysis of the differences between clinical text found in electronic health records and biomedical text found in online journals, books, and conference papers, as well as a presentation of various text mining tools that have been developed in both university and commercial settings. 1.1 Introduction The corpus of biomedical information is growing very rapidly. New and useful results appear every day in research publications, from journal articles to book chapters to workshop and conference proceedings. Many of these publications are available online through journal citation databases such as Medline – a subset of the PubMed interface that enables access to Medline publications – which is among the largest and most well-known online databases for indexing profes- sional literature. Such databases and their associated search engines contain important research work in the biological and medical domain, including recent findings pertaining to diseases, symptoms, and medications.
    [Show full text]
  • LDA V. LSA: a Comparison of Two Computational Text Analysis Tools for the Functional Categorization of Patents
    LDA v. LSA: A Comparison of Two Computational Text Analysis Tools for the Functional Categorization of Patents Toni Cvitanic1, Bumsoo Lee1, Hyeon Ik Song1, Katherine Fu1, and David Rosen1! ! 1Georgia Institute of Technology, Atlanta, GA, USA (tcvitanic3, blee300, hyeoniksong) @gatech.edu (katherine.fu, david.rosen) @me.gatech.edu! !! Abstract. One means to support for design-by-analogy (DbA) in practice involves giving designers efficient access to source analogies as inspiration to solve problems. The patent database has been used for many DbA support efforts, as it is a pre- existing repository of catalogued technology. Latent Semantic Analysis (LSA) has been shown to be an effective computational text processing method for extracting meaningful similarities between patents for useful functional exploration during DbA. However, this has only been shown to be useful at a small-scale (100 patents). Considering the vastness of the patent database and realistic exploration at a large- scale, it is important to consider how these computational analyses change with orders of magnitude more data. We present analysis of 1,000 random mechanical patents, comparing the ability of LSA to Latent Dirichlet Allocation (LDA) to categorize patents into meaningful groups. Resulting implications for large(r) scale data mining of patents for DbA support are detailed. Keywords: Design-by-analogy ! Patent Analysis ! Latent Semantic Analysis ! Latent Dirichlet Allocation ! Function-based Analogy 1 Introduction Exposure to appropriate analogies during early stage design has been shown to increase the novelty, quality, and originality of generated solutions to a given engineering design problem [1-4]. Finding appropriate analogies for a given design problem is the largest challenge to practical implementation of DbA.
    [Show full text]
  • Impact of Word Embedding Methods on Performance of Sentiment Analysis with Machine Learning Techniques
    한국컴퓨터정보학회논문지 Journal of The Korea Society of Computer and Information Vol. 25 No. 8, pp. 181-188, August 2020 JKSCI https://doi.org/10.9708/jksci.2020.25.08.181 Impact of Word Embedding Methods on Performance of Sentiment Analysis with Machine Learning Techniques 1)Hoyeon Park*, Kyoung-jae Kim** *Ph.D. Candidate, Dept. of MIS, Graduate School, Dongguk University, Seoul, Korea **Professor, Dept. of MIS, Business School, Dongguk University, Seoul, Korea [Abstract] In this study, we propose a comparative study to confirm the impact of various word embedding techniques on the performance of sentiment analysis. Sentiment analysis is one of opinion mining techniques to identify and extract subjective information from text using natural language processing and can be used to classify the sentiment of product reviews or comments. Since sentiment can be classified as either positive or negative, it can be considered one of the general classification problems. For sentiment analysis, the text must be converted into a language that can be recognized by a computer. Therefore, text such as a word or document is transformed into a vector in natural language processing called word embedding. Various techniques, such as Bag of Words, TF-IDF, and Word2Vec are used as word embedding techniques. Until now, there have not been many studies on word embedding techniques suitable for emotional analysis. In this study, among various word embedding techniques, Bag of Words, TF-IDF, and Word2Vec are used to compare and analyze the performance of movie review sentiment analysis. The research data set for this study is the IMDB data set, which is widely used in text mining.
    [Show full text]
  • Automated Citation Sentiment Analysis Using High Order N-Grams: a Preliminary Investigation
    Turkish Journal of Electrical Engineering & Computer Sciences Turk J Elec Eng & Comp Sci (2018) 26: 1922 – 1932 http://journals.tubitak.gov.tr/elektrik/ © TÜBİTAK Research Article doi:10.3906/elk-1712-24 Automated citation sentiment analysis using high order n-grams: a preliminary investigation Muhammad Touseef IKRAM1;∗,, Muhammad Tanvir AFZAL1, Naveed Anwer BUTT2, 1Department of Computer Science, Capital University of Science and Technology, Islamabad, Pakistan 2Department of Computer Science, University of Gujrat, Gujrat, Pakistan Received: 03.12.2017 • Accepted/Published Online: 02.02.2018 • Final Version: 27.07.2018 Abstract: Scientific papers hold an association with previous research contributions (i.e. books, journals or conference papers, and web resources) in the form of citations. Citations are deemed as a link or relatedness of the previous work to the cited work. The nature of the cited material could be supportive (positive), contrastive (negative), or objective (neutral). Extraction of the author’s sentiment towards the cited scientific articles is an emerging research discipline due to various linguistic differences between the citation sentences and other domains of sentiment analysis. In this paper, we propose a technique for the identification of the sentiment of the citing author towards the cited paper by extracting unigram, bigram, trigram, and pentagram adjective and adverb patterns from the citation text. After POS tagging of the citation text, we use the sentence parser for the extraction of linguistic features comprising adjectives, adverbs, and n-grams from the citation text. A sentiment score is then assigned to distinguish them as positive, negative, and neutral. In addition, the proposed technique is compared with manually classified citation text and 2 commercial tools, namely SEMANTRIA and THEYSAY, to determine their applicability to the citation corpus.
    [Show full text]
  • Alignment-Based Topic Extraction Using Word Embedding
    Alignment-Based Topic Extraction Using Word Embedding [0000 0003 3108 8407] [0000 0002 8408 3944] Tyler Newman − − − and Paul Anderson − − − College of Charleston, Charleston SC 29424, USA [email protected] [email protected] Abstract. Being able to extract targeted topics from text can be a useful tool for understanding the large amount of textual data that exists in various domains. Many methods have surfaced for building frameworks that can successfully extract this topic data. However, it is often the case that a large number of training samples must be labeled properly, which requires both time and domain knowledge. This paper introduces new alignment-based methods for predicting topics within textual data that minimizes the dependence upon a large, properly-labeled training set. Leveraging Word2Vec word embeddings trained using unlabeled data in a semi-supervised approach, we are able to reduce the amount of labeled data necessary during the text annotation process. This allows for higher prediction levels to be attained in a more time-efficient manner with a smaller sample size. Our method is evaluated on both a publicly available Twitter sentiment classification dataset and on a real estate text classification dataset with 30 topics. Keywords: Topic extraction · Text annotation · Text classification · Word vectors · Text tagging 1 Introduction Finding specific topics within textual data is an important task for many do- mains. A multitude of approaches for achieving this task have appeared in recent years [14], no doubt due to the ever growing amount of textual data available to organizations and researchers. In the most straightforward case, topic labels are known a priori and non-domain experts can be trained to manually label examples using systems such as Mechanical Turk [4].
    [Show full text]