Relatedness Of Terms Research Articles

A Text Analytics Framework for Supplier Capability Scoring Supported by Normalized Google Distance and Semantic Similarity Measurement Methods

AbstractThe unstructured data available on the websites of manufacturing suppliers and contractors can provide valuable insights into their technological and organizational capabilities. However, since the capability data are often represented in an unstructured and informal fashion using natural language text, they do not lend themselves well to computational analysis. The objective of this work is to propose framework to enable automated classification and ranking of manufacturing suppliers based on their online capability descriptions in the context of a supplier search and discovery use case. The proposed text analytics framework is supported by a formal thesaurus that uses Simple Knowledge Organization System (SKOS) that provides lexical and structural semantics. Normalized Google Distance (NGD) is used as the metric for measuring the relatedness of terms when ranking suppliers based on their similarities with the queried capabilities. The proposed framework is validated experimentally using a hypothetical supplier search scenario. The results indicate that the generated ranked list is highly correlated with human judgment, especially when the search space is partitioned into multiple classes of suppliers with distinct capabilities. However, the correlation decreases when multiple overlapping classes of suppliers are merged together to form a heterogenous search space. The proposed framework can support supplier screening and discovery solutions by improving the precision, reliability, and intelligence of their underlying search engines.

Climate Change, Pollution, Deforestation, and Mental Health: Research Trends, Gaps, and Ethical Considerations.

Climate change, pollution, and deforestation have a negative impact on global mental health. There is an environmental justice dimension to this challenge as wealthy people and high-income countries are major contributors to climate change and pollution, while poor people and low-income countries are heavily affected by the consequences. Using state-of-the art data mining, we analyzed and visualized the global research landscape on mental health, climate change, pollution and deforestation over a 15-year period. Metadata of papers were exported from PubMed®, and both relevance and relatedness of terms in different time frames were computed using VOSviewer. Co-occurrence graphs were used to visualize results. The development of exemplary terms over time was plotted separately. The number of research papers on mental health and environmental challenges is growing in a linear fashion. Major topics are climate change, chemical pollution, including psychiatric medication in wastewater, and neurobiological effects. Research on specific psychiatric syndromes and diseases, particularly on their ethical and social aspects is less prominent. There is a growing body of research literature on links between mental health, climate change, pollution, and deforestation. This research provides a graphic overview to mental healthcare professionals and political stakeholders. Social and ethical aspects of the climate change-mental health link have been neglected, and more research is needed.

To whose good? Directions and gaps in psychiatric research.

Psychiatry's evidence-, implementation-, and treatment-gaps. The aim of this study is to uncover current trends and gaps in psychiatric research. Understanding where psychiatric research is going and where there might be blind spots is important to better align it with global mental health challenges and with service users' needs. 10 top-ranking scientific journals (highest impact factors) in psychiatry were identified for 3 years (1999, 2009, 2019) using Clarivate Analytics. Metadata of all papers published by these journals in the index years were downloaded, and the relevance and relatedness of terms from all titles and abstracts were computed and visualized using VOSviewer. In 1999, prominent themes included schizophrenia and novel antipsychotics as well as research on families. Ten and 20 years later, neurobiological research, especially genetic and animal studies, had gained importance. Social and psychological themes were less present across all three time points. In high-ranking psychiatric journals, neurobiological research appears to gain importance while social themes are under-represented. In view of challenges such as implementation gaps, marginalization of people with severe mental illness and mental health risks through social inequality, there seems to be a dissociation between research and patient needs. We suggest a systems approach to bring together different kinds of knowledge.

Word embeddings for application in geosciences: development, evaluation, and examples of soil-related concepts

Abstract. A large amount of descriptive information is available in geosciences. This information is usually considered subjective and ill-favoured compared with its numerical counterpart. Considering the advances in natural language processing and machine learning, it is possible to utilise descriptive information and encode it as dense vectors. These word embeddings, which encode information about a word and its linguistic relationships with other words, lay on a multidimensional space where angles and distances have a linguistic interpretation. We used 280 764 full-text scientific articles related to geosciences to train a domain-specific language model capable of generating such embeddings. To evaluate the quality of the numerical representations, we performed three intrinsic evaluations: the capacity to generate analogies, term relatedness compared with the opinion of a human subject, and categorisation of different groups of words. As this is the first attempt to evaluate word embedding for tasks in the geosciences domain, we created a test suite specific for geosciences. We compared our results with general domain embeddings commonly used in other disciplines. As expected, our domain-specific embeddings (GeoVec) outperformed general domain embeddings in all tasks, with an overall performance improvement of 107.9 %. We also presented an example were we successfully emulated part of a taxonomic analysis of soil profiles that was originally applied to soil numerical data, which would not be possible without the use of embeddings. The resulting embedding and test suite will be made available for other researchers to use and expand upon.

Term evaluation metrics in imbalanced text categorization

AbstractThis paper proposes four novel term evaluation metrics to represent documents in the text categorization where class distribution is imbalanced. These metrics are achieved from the revision of the four common term evaluation metrics:chi-square,information gain,odds ratio, andrelevance frequency. While the common metrics require a balanced class distribution, our proposed metrics evaluate the document terms under an imbalanced distribution. They calculate the degree of relatedness of terms with respect to minor and major classes by considering their imbalanced distribution. Using these metrics in the document representation makes a better distinction between the documents of the minor and major classes and improves the performance of machine learning algorithms. The proposed metrics are assessed over three popular benchmarks (two subsets of Reuters-21578 and WebKB) by using four classification algorithms: support vector machines, naive Bayes, decision trees, and centroid-based classifiers. Our empirical results indicate that the proposed metrics outperform the common metrics in the imbalanced text categorization.

A novel MEDLINE topic indexing method using image presentation

MEDLINE is one of the largest databases of biomedical literatures. The search results from MEDLINE for medical terms are in the form of lists of articles with PubMed IDs. To further explore and select articles that may help identify potentially interesting interactions between terms, users need to navigate through the lists of URLs to retrieve and read actual articles to find relevancies among these terms. Such work becomes extremely time consuming and unbearably tedious when each query returns tens of thousands results with an uncertain recall rate. To overcome this problem, we develop a topic-specific image indexing and presentation method for discovering interactions or relatedness of medical terms from MEDLINE, based on which a prototype tool is implemented to help discover interactions between terms of types of diseases. The merits of the method is illustrated by search examples using the tool and MEDLINE abstract dataset.

Semantic text classification: A survey of past and recent advances

Automatic text classification is the task of organizing documents into pre-determined classes, generally using machine learning algorithms. Generally speaking, it is one of the most important methods to organize and make use of the gigantic amounts of information that exist in unstructured textual format. Text classification is a widely studied research area of language processing and text mining. In traditional text classification, a document is represented as a bag of words where the words in other words terms are cut from their finer context i.e. their location in a sentence or in a document. Only the broader context of document is used with some type of term frequency information in the vector space. Consequently, semantics of words that can be inferred from the finer context of its location in a sentence and its relations with neighboring words are usually ignored. However, meaning of words, semantic connections between words, documents and even classes are obviously important since methods that capture semantics generally reach better classification performances. Several surveys have been published to analyze diverse approaches for the traditional text classification methods. Most of these surveys cover application of different semantic term relatedness methods in text classification up to a certain degree. However, they do not specifically target semantic text classification algorithms and their advantages over the traditional text classification. In order to fill this gap, we undertake a comprehensive discussion of semantic text classification vs. traditional text classification. This survey explores the past and recent advancements in semantic text classification and attempts to organize existing approaches under five fundamental categories; domain knowledge-based approaches, corpus-based approaches, deep learning based approaches, word/character sequence enhanced approaches and linguistic enriched approaches. Furthermore, this survey highlights the advantages of semantic text classification algorithms over the traditional text classification algorithms.

Semantic relatedness and similarity of biomedical terms: examining the effects of recency, size, and section of biomedical publications on the performance of word2vec

BackgroundUnderstanding semantic relatedness and similarity between biomedical terms has a great impact on a variety of applications such as biomedical information retrieval, information extraction, and recommender systems. The objective of this study is to examine word2vec’s ability in deriving semantic relatedness and similarity between biomedical terms from large publication data. Specifically, we focus on the effects of recency, size, and section of biomedical publication data on the performance of word2vec.MethodsWe download abstracts of 18,777,129 articles from PubMed and 766,326 full-text articles from PubMed Central (PMC). The datasets are preprocessed and grouped into subsets by recency, size, and section. Word2vec models are trained on these subtests. Cosine similarities between biomedical terms obtained from the word2vec models are compared against reference standards. Performance of models trained on different subsets are compared to examine recency, size, and section effects.ResultsModels trained on recent datasets did not boost the performance. Models trained on larger datasets identified more pairs of biomedical terms than models trained on smaller datasets in relatedness task (from 368 at the 10% level to 494 at the 100% level) and similarity task (from 374 at the 10% level to 491 at the 100% level). The model trained on abstracts produced results that have higher correlations with the reference standards than the one trained on article bodies (i.e., 0.65 vs. 0.62 in the similarity task and 0.66 vs. 0.59 in the relatedness task). However, the latter identified more pairs of biomedical terms than the former (i.e., 344 vs. 498 in the similarity task and 339 vs. 503 in the relatedness task).ConclusionsIncreasing the size of dataset does not always enhance the performance. Increasing the size of datasets can result in the identification of more relations of biomedical terms even though it does not guarantee better precision. As summaries of research articles, compared with article bodies, abstracts excel in accuracy but lose in coverage of identifiable relations.

Unsupervised ensemble ranking of terms in electronic health record notes based on their importance to patients

BackgroundAllowing patients to access their own electronic health record (EHR) notes through online patient portals has the potential to improve patient-centered care. However, EHR notes contain abundant medical jargon that can be difficult for patients to comprehend. One way to help patients is to reduce information overload and help them focus on medical terms that matter most to them. Targeted education can then be developed to improve patient EHR comprehension and the quality of care. ObjectiveThe aim of this work was to develop FIT (Finding Important Terms for patients), an unsupervised natural language processing (NLP) system that ranks medical terms in EHR notes based on their importance to patients. MethodsWe built FIT on a new unsupervised ensemble ranking model derived from the biased random walk algorithm to combine heterogeneous information resources for ranking candidate terms from each EHR note. Specifically, FIT integrates four single views (rankers) for term importance: patient use of medical concepts, document-level term salience, word co-occurrence based term relatedness, and topic coherence. It also incorporates partial information of term importance as conveyed by terms’ unfamiliarity levels and semantic types. We evaluated FIT on 90 expert-annotated EHR notes and used the four single-view rankers as baselines. In addition, we implemented three benchmark unsupervised ensemble ranking methods as strong baselines. ResultsFIT achieved 0.885 AUC-ROC for ranking candidate terms from EHR notes to identify important terms. When including term identification, the performance of FIT for identifying important terms from EHR notes was 0.813 AUC-ROC. Both performance scores significantly exceeded the corresponding scores from the four single rankers (P<0.001). FIT also outperformed the three ensemble rankers for most metrics. Its performance is relatively insensitive to its parameter. ConclusionsFIT can automatically identify EHR terms important to patients. It may help develop future interventions to improve quality of care. By using unsupervised learning as well as a robust and flexible framework for information fusion, FIT can be readily applied to other domains and applications.

A Novel Approach for Computing Semantic Relatedness of Geographic Terms

Background: Computing semantic relatedness measures are extensively employed in the field of Natural Language Processing (NLP) and play pivotal role in Geographic Information Science (GIS). Methods/Analysis: Noteworthy, despite the significance of semantic relatedness in geographic domain, its role has been almost ignored. While most of the proposed measures in this context are only able to compute semantic similarity, in this paper, the notion of geosemantic relatedness is discussed and from which a novel approach for computing semantic relatedness of geographic terms is proposed. The proposed method utilizes term’s definition from geographic lexicon. Whereas lexical definition demarcates the boundaries of a term and provides valuable semantic space for deducting the meaning of a term, it can have prominent impact in the efficiency of the proposed approach. Furthermore, this approach exploits Wikipedia as semantic resource that has considerable performance in application of semantic relatedness. Finding: The cognitive plausibility of the proposed approach is evaluated on GeReSiD dataset. Compared to the previous state of the arts, using proposed approach results significant improvement in correlation of computed relatedness score with human judgment to 0.73. Conclusion: Additionally, the proposed approach not only prospers higher perception and adoption, but also it has greater applicability in real world problems and is confronted with fewer limitations. Moreover, the proposed method can perform disambiguation in geographic domain properly.

Enhancing passage retrieval in log files by query expansion based on explicit and pseudo relevance feedback

Passage retrieval is usually defined as the task of searching for passages which may contain the answer for a given query. While these approaches are very efficient when dealing with texts, applied to log files (i.e. semi-structured data containing both numerical and symbolic information) they usually provide irrelevant or useless results. Nevertheless one appealing way for improving the results could be to consider query expansions that aim at adding automatically or semi-automatically additional information in the query to improve the reliability and accuracy of the returned results. In this paper, we present a new approach for enhancing the relevancy of queries during a passage retrieval in log files. It is based on two relevance feedback steps. In the first one, we determine the explicit relevance feedback by identifying the context of the requested information within a learning process. The second step is a new kind of pseudo relevance feedback. Based on a novel term weighting measure it aims at assigning a weight to terms according to their relatedness to queries. This measure, called TRQ (Term Relatedness to Query), is used to identify the most relevant expansion terms.The main advantage of our approach is that is can be applied both on log files and documents from general domains. Experiments conducted on real data from logs and documents show that our query expansion protocol enables retrieval of relevant passages.

CPRel: Semantic Relatedness Computation Using Wikipedia based Context Profiles

Semantic relatedness is a well known problem with its sig- nicance ranging from computational linguistics to Natural language Processing applications. Relatedness computation is restricted by the amount of common sense and background knowledge required to relate any two terms. This paper proposes a novel model of relatedness using context prole built on features extracted from encyclopedic knowledge. Proposed research makes use of Wikipedia to represent the context of a word in the high dimensional space of Wikipedia labels. Semantic relat- edness of a word pair is then assessed by comparing their corresponding context proles based on three dierent weighting schemes using tradi- tional Cosine similarity metrics. To evaluate proposed relatedness ap- proach, three well known benchmark datasets are used and it is shown that Wikipedia article contents can be used eectively to compute term relatedness. The experiments demonstrate that the proposed approach is computationally cheap as well as eective when correlated with human judgments.

Using a Search Engine-Based Mutually Reinforcing Approach to Assess the Semantic Relatedness of Biomedical Terms

BackgroundDetermining the semantic relatedness of two biomedical terms is an important task for many text-mining applications in the biomedical field. Previous studies, such as those using ontology-based and corpus-based approaches, measured semantic relatedness by using information from the structure of biomedical literature, but these methods are limited by the small size of training resources. To increase the size of training datasets, the outputs of search engines have been used extensively to analyze the lexical patterns of biomedical terms.Methodology/Principal FindingsIn this work, we propose the Mutually Reinforcing Lexical Pattern Ranking (ReLPR) algorithm for learning and exploring the lexical patterns of synonym pairs in biomedical text. ReLPR employs lexical patterns and their pattern containers to assess the semantic relatedness of biomedical terms. By combining sentence structures and the linking activities between containers and lexical patterns, our algorithm can explore the correlation between two biomedical terms.Conclusions/SignificanceThe average correlation coefficient of the ReLPR algorithm was 0.82 for various datasets. The results of the ReLPR algorithm were significantly superior to those of previous methods.

Using proximity to compute semantic relatedness in RDF graphs

Extracting the semantic relatedness of terms is an important topic in several areas, including data mining, information retrieval and web recommendation. This paper presents an approach for computing the semantic relatedness of terns in RDF graphs based on the notion of proximity. It proposes a formal definition of proximity in terms of the set paths connecting two concept nodes, and an algorithm for finding this set and computing proximity with a given error margin. This algorithm was implemented on a tool called Shakti that extracts relevant ontological data for a given domain from DBpedia - a community effort to extract structured data from the Wikipedia. To validate the proposed approach Shakti was used to recommend web pages on a Portuguese social site related to alternative music and the results of that experiment are also reported.

Automatic thesaurus generation for Chinese documents

AbstractThis article reports an approach to automatic thesaurus construction for Chinese documents. An effective Chinese keyword extraction algorithm is first presented. Experiments showed that for each document an average of 33% keywords unknown to a lexicon of 123,226 terms could be identified by this algorithm. Of these unregistered words, only 8.3% of them are illegal. Keywords extracted from each document are further filtered for term association analysis. Association weights larger than a threshold are then accumulated over all the documents to yield the final term pair similarities. Compared to previous studies, this method speeds up the thesaurus generation process drastically. It also achieves a similar percentage level of term relatedness.

Structure and process in semantic memory: evidence from event-related brain potentials and reaction times.

Through scalp measurements of the electrical activity of the brain (event-related potentials, or ERPs) recorded while subjects verified the truth of sentences relating exemplars and categories (e.g., ALL DOGS ARE ANIMALS), inferences were made about aspects of semantic processing that were not directly reflected by overt responses. In particular, it is suggested that a negative ERP component that peaks about 400 ms after the onset of the sentence predicate (i.e., N400) is sensitive to structural aspects of semantic memory. The amplitude of this component was modulated by the relatedness of the subject and predicate terms, as well as the hierarchical level of both these terms, but was not sensitive to the truth value of a sentence.