Explore the vast range of titles available.

Qiu, W., 2020. Analysis of radiation effect of coastal economic circle based on space vector model. In: Liu, X. and Zhao, L. (eds.), Today's Modern Coastal Society: Technical and Sociological Aspects of Coastal Research. Journal of Coastal Research, Special Issue No. 111, pp. 322–325. Coconut Creek (Florida), ISSN 0749-0208. By systematically exploring the temporal and spatial evolution of the industrial layout in the coastal area, this paper summarizes the driving factors that affect the formation of the industrial layout in the coastal area and provides an in-depth discussion of the regional economic radiation effects. Using the vector space model, the relationship between the economic activity and the industrial radiation effect of the coastal area is constructed to explore the radiation of the economy of the coastal area in space. Based on the theoretical framework of the functional mechanism of the industrial layout in the coastal area, the location entropy analysis method is used to verify the industrial radiation degree, the economic industry correlation degree, the relationship with the industrial layout, and the influence of economic-related factors on the industrial layout in the coastal area, so as to achieve the purpose of scientific management. The results of the empirical analysis demonstrate the radiation effect of the economic industry in the coastal area.

Vertical Search Engine provides a professional search compared with the traditional search engine. All of the data searched by vertical search engine is relative with some one theme, which is decided by users. Usually Vector Space Model is used for judging the relativity between data in the web and the decided theme. But when elements of the theme appear repeatedly, their order is not considered by Vector Space Model. Adding a new element, the Evolved Vector Space Model is provided. The experiments show that the new model has fixed the problem and have a better performance in judging relativity.

Traditional Web news media retrieval technology can only meet the specific requirements of customers. Because of its universal characteristics, it cannot meet the needs of different environments, different purposes and different times simultaneously. Researchers have proposed a search method for online news media, which is used for computing the semantic grouping vector space model. The customer's interest model is analyzed through the characteristics of the user's different classification areas. In this paper, we propose a vector space model that performs semantic grouping based on feature words. The model divides four groups that are relatively independent in the meaning of feature words in a news report: time, place, person, and event, and then form four vector spaces, and calculate the weight value and similarity of each vector space. Theoretical analysis and experimental results show that the improved model is suitable for searching Web news information, and improves the calibration rate, calibration rate and query speed.

During literature reviews, and specially when conducting systematic literature reviews, finding and screening relevant papers during scientific document search may involve managing and processing large amounts of unstructured text data. In those cases where the search topic is difficult to establish or has fuzzy limits, researchers require to broaden the scope of the search and, in consequence, data from retrieved scientific publications may become huge and uncorrelated. However, through a convenient analysis of these data the researcher may be able to discover new knowledge which may be hidden within the search output, thus exploring the limits of the search and enhancing the review scope. With that aim, this paper presents an iterative methodology that applies text mining and machine learning techniques to a downloaded corpus of abstracts from scientific databases, combining automatic processing algorithms with tools for supervised decision-making in an iterative process sustained on the researchers’ judgement, so as to adapt, screen and tune the search output. The paper ends showing a working example that employs a set of developed scripts that implement the different stages of the proposed methodology.

This study aims to find articles and clauses from the 1945 Constitution (UUD 1945) using the Vector Space Model method that calculates the similarity of many documents. One document is represented by one clause from each article of the 1945 Constitution. The next step is pre-processing by deleting unnecessary words (stopwords) and changing it into basic words (stemmer) in the Indonesian language. Each document will be indexed to speed up query and simplify the weighting. Words weighting in documents is performed using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm by calculating the frequency of words in documents and all documents. The document search results will be presented in the ranking with the largest number of scoring appears at the top (descend sorting). The word search in this system more or less takes 90-100 milliseconds in 73 documents.

We explore the potential of a popular distributional semantics vector space model, word2vec , for capturing meaningful relationships in ecological (complex polyphonic) music. More precisely, the skip-gram version of word2vec is used to model slices of music from a large corpus spanning eight musical genres. In this newly learned vector space, a metric based on cosine distance is able to distinguish between functional chord relationships, as well as harmonic associations in the music. Evidence, based on cosine distance between chord-pair vectors, suggests that an implicit circle-of-fifths exists in the vector space. In addition, a comparison between pieces in different keys reveals that key relationships are represented in word2vec space. These results suggest that the newly learned embedded vector representation does in fact capture tonal and harmonic characteristics of music, without receiving explicit information about the musical content of the constituent slices. In order to investigate whether proximity in the discovered space of embeddings is indicative of ‘semantically-related’ slices, we explore a music generation task, by automatically replacing existing slices from a given piece of music with new slices. We propose an algorithm to find substitute slices based on spatial proximity and the pitch class distribution inferred in the chosen subspace. The results indicate that the size of the subspace used has a significant effect on whether slices belonging to the same key are selected. In sum, the proposed word2vec model is able to learn music-vector embeddings that capture meaningful tonal and harmonic relationships in music, thereby providing a useful tool for exploring musical properties and comparisons across pieces, as a potential input representation for deep learning models, and as a music generation device.

ContextRepresenting the textual semantics of bug reports is a key component of bug report management (BRM) techniques. Existing studies mainly use classical information retrieval-based (IR-based) approaches, such as the vector space model (VSM) to do semantic extraction. Little attention is paid to exploring whether word embedding (WE) models from the natural language process could help BRM tasks.ObjectiveTo have a general view of the potential of word embedding models in representing the semantics of bug reports and attempt to provide some actionable guidelines in using semantic retrieval models for BRM tasks.MethodWe studied the efficacy of five widely recognized WE models for six BRM tasks on 20 widely-used products from the Eclipse and Mozilla foundations. Specifically, we first explored the suitable machine learning techniques under the use of WE models and the suitable WE model for BRM tasks. Then we studied whether WE models performed better than classical VSM. Last, we investigated whether WE models fine-tuned with bug reports outperformed general pre-trained WE models.Key ResultsThe Random Forest (RF) classifier outperformed other typical classifiers under the use of different WE models in semantic extraction.We rarely observed statistically significant performance differences among five WE models in five BRM classification tasks, but we found that small-dimensional WE models performed better than larger ones in the duplicate bug report detection task. Among three BRM tasks (i.e., bug severity prediction, reopened bug prediction, and duplicate bug report detection) that showed statistically significant performance differences, VSM outperformed the studied WE models. We did not find performance improvement after we fine-tuned general pre-trained BERT with bug report data.ConclusionPerformance improvements of using pre-trained WE models were not observed in studied BRM tasks. The combination of RF and traditional VSM was found to achieve the best performance in various BRM tasks.

Software traceability links are established between diverse artifacts of the software development process in order to support tasks such as compliance analysis, safety assurance, and requirements validation. However, practice has shown that it is difficult and costly to create and maintain trace links in non-trivially sized projects. For this reason, many researchers have proposed and evaluated automated approaches based on information retrieval and deep-learning. Generating trace links automatically can also be challenging – especially in multi-national projects which include artifacts written in multiple languages. The intermingled language use can reduce the efficiency of automated tracing solutions. In this work, we analyze patterns of intermingled language that we observed in several different projects, and then comparatively evaluate different tracing algorithms. These include Information Retrieval techniques, such as the Vector Space Model (VSM), Latent Semantic Indexing (LSI), Latent Dirichlet Allocation (LDA), and various models that combine mono- and cross-lingual word embeddings with the Generative Vector Space Model (GVSM), and a deep-learning approach based on a BERT language model. Our experimental analysis of trace links generated for 14 Chinese-English projects indicates that our MultiLingual Trace-BERT approach performed best in large projects with close to 2-times the accuracy of the best IR approach, while the IR-based GVSM with neural machine translation and a monolingual word embedding performed best on small projects.

Taking urban cinema as the research object, this study creatively integrates the content analysis method and LDA thematic model to construct a multidimensional analysis framework, aiming to explain the image-based expression mechanism of youth culture. The dimensionality reduction of textual features is realized through vector space modeling, and the co-occurrence frequency of youth culture elements is quantified by combining with n-meta-language modeling. The LDA thematic feature model is proposed to integrate text analysis, and the LDA-Kmeans method is used for thematic clustering to identify the core themes of youth lying and involutional “subculture” identity construction weights. In the model construction, the coding layer that integrates the theme features is innovatively designed, and the classification layer enhances the semantic information processing by converting logical vectors into probabilities using the Softmax function to increase the accuracy, recall and F1 value of this paper’s model on the dataset to more than 95%. In addition, the results of the case study show that the youth culture from the content of the movie of lying down mainly presents four themes such as the reasons for lying down and inner emotions of the youth. The perspective of involution presents four themes such as seriousness of involution and educational involution from the perspective of young people. The discourse expression of lie flat and introspection reflects the current situation of contemporary youth’s life and inner feelings. Finally, this paper analyzes the causes of the popularity of lie flat and introspection as well as the subcultural representations of youth.

The focused crawler downloads web pages related to the given topic from the Internet. In many research studies, most of focused crawler predict the priority values of unvisited hyperlinks by integrating the topic similarities based on the text similarity model and equivalent weighted factors based on the manual method. However, in these focused crawlers, there are flaws in the text similarity models, and weighted factors are arbitrarily determined for calculating priorities of unvisited URLs. To solve these problems, this paper proposes a semantic and intelligent focused crawler based on the Semantic Vector Space Model (SVSM) and the Membrane Computing Optimization Algorithm (MCOA). Firstly, the SVSM method is used to calculate topic similarities between texts and the given topic. Secondly, the MCOA method is used to optimize four weighted factors based on the evolution rules and the communication rule. Finally, this proposed focused crawler predicts the priority of each unvisited hyperlink by integrating the topic similarities of four texts and the optimal four weighted factors. The experiment results indicate that the proposed SVSM-MCOA Crawler improve the evaluation indicators compared with the other four focused crawlers. In conclusion, the proposed SVSM and MCOA method promotes the focused crawler to have semantic understanding and intelligent learning ability.