The algorithm of building the hierarchical contextual framework of textual corpora

Rizun, Nina; Waloszek, Wojciech

doi:10.1109/intelcis.2017.8260064

Cited by 6 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• on the 1st level of the hierarchy is equal to 5 for SNCS and is equal to 4 for SNSC; • on the 2nd level of the hierarchy is equal to 4 for SNCS and is equal to 3 for SNSC. The hierarchical structure of the contextually-oriented corpus (HC), created as a two-point (positive/negative classes) structure of the sets of paragraphs, semantically close to revealed topics with contextual dictionaries (for each separate layer and after adjustment-on the 1st level of topics) is presented in Table 12 [8,38]. The contextual labels (CL) of the topics were assigned automatically based on the terms with the highest frequency in each topic.…”

Section: Resultsmentioning

confidence: 99%

“…In this step, considering the specificity of the chosen dataset language as well as limited number of existing methods for the analysis of the text in Polish [45], in addition to the standard text pre-processing procedures, the authors have proposed the specific text adaptation procedure [8].…”

Section: Sentiment Classification Based On the Manually Created Cbsd mentioning

confidence: 99%

“…In recent years, a number of methods for detecting topics and sentiment analysis have been proposed. But, firstly, many of these methods are devoted to the improvement of the theory of Latent Semantic Analysis and its use to identify hidden contextual links between documents [1][2][3][4] or improving the recognition of topics while using the knowledge about words probability distributions within the text collection [5][6][7][8][9][10][11][12][13][14][15][16][17], for example Bayesian nonparametric topic models [5][6][7]. The results of these studies do represent a significant contribution to the development of science.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations

Rizun

Taranenko

Waloszek³

2018

Information

Self Cite

View full text Add to dashboard Cite

The research presents the methodology of improving the accuracy in sentiment classification in the light of modelling the latent semantic relations (LSR). The objective of this methodology is to find ways of eliminating the limitations of the discriminant and probabilistic methods for LSR revealing and customizing the sentiment classification process (SCP) to the more accurate recognition of text tonality. This objective was achieved by providing the possibility of the joint usage of the following methods: (1) retrieval and recognition of the hierarchical semantic structure of the text and (2) development of the hierarchical contextually-oriented sentiment dictionary in order to perform the context-sensitive SCP. The main scientific contribution of this research is the set of the following approaches: at the phase of LSR revealing (1) combination of the discriminant and probabilistic models while applying the rules of adjustments to obtain the final joint result; at all SCP phases (2) considering document as a complex structure of topically completed textual components (paragraphs) and (3) taking into account the features of persuasive documents’ type. The experimental results have demonstrated the enhancement of the SCP accuracy, namely significant increase of average values of recall and precision indicators and guarantee of sufficient accuracy level.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Sentiment Classification Based On the Manually Created Cbsd mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations

Rizun

Taranenko

Waloszek³

2018

Information

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the first stage of the methodology development, the authors take into account specificity of the chosen case study and the results of previous research results [29]. These results suggest the possibility of building the Hierarchical structure of the Contextually-Oriented Corpus (COHC) via application of the Discriminant and Probabilistic Methods of the Latent Dirichlet Allocation (LDA) and Latent Semantic Relations Analysis (LSA) [28,30].…”

Section: B Contextual Component Of the Corpora's Contextually-orientmentioning

confidence: 99%

“…For finding the answers for these questions, the following assumptions (A) were formulated: A1: Taking into account the specificity of the chosen case study [16,17,29], assume that each paragraph could be interpreted as a topically completed textual component (TCTC).…”

Section: Rq_1: Does Creation Of the Contextual Structure Of The Corpumentioning

confidence: 99%

Methodology of Constructing and Analyzing the Hierarchical Contextually-Oriented Corpora

Rizun

Taranenko

2018

Annals of Computer Science and Information Systems

Self Cite

View full text Add to dashboard Cite

Methodology of Constructing and Analyzing the Hierarchical structure of the Contextually-Oriented Corpora was developed. The methodology contains the following steps: Contextual Component of the Corpora's Structure Building; Text Analysis of the Contextually-Oriented Hierarchical Corpus. Main contribution of this study is the following: hierarchical structure of the Corpus provides advanced possibilities for identification of the Morphological and Structural features of texts of different tonalities; Contextual, Morphological and Structural specificity of texts with tonality, originally assigned by the authors, has significant differences; exist the certain thought and writing style Templates, under the influence of which the formation of texts of various tonalities takes place. As basic features of such templates for the texts of the two basic (positive/negative) tonalities could be used: Contextual Structure, Morphological Types, Emotional Features, Writing Style and Vocabulary Richness. For verification of the proposed methodology, a case study of Polish-language film reviews Dataset was used.

show abstract

Improving the Accuracy in Text Classification Methodology in Light of Modelling the Latent Semantic Relations

Rizun¹,

Taranenko²,

Waloszek³

2018

Preprint

Self Cite

View full text Add to dashboard Cite

The research presents the Methodology of Improving the Accuracy in Text Classification in Light of Modelling the Latent Semantic Relations (LSR). The aim of this Methodology is to find the ways of eliminating the Limitations of Discriminant and Probabilistic methods for LSR revealing and customizing the Text Classification Process to the more accurate recognition of the text tonality. This aim should be achieved by using the knowledge about the text’s Hierarchical Semantic Context in the form of Corpora-based Hierarchical Sentiment Dictionary. The main scientific contribution of this research is the following set of approaches to improve the qualitative characteristics of Text Classification process: combination of the Discriminant and Probabilistic methods allowing to decrease the influences of the Limitations of these methods on the LSR revealing process; considering each document as a complex structure allowing to estimate documents integrally by separated classification of topically completed textual component (paragraphs); taking into account the features of Argumentative type of documents (Reviews) allowing to use the author’s subjective evaluation of text tonality for development the Text Classification methodology. Tonality, expressed by the Review’s author, has a significant, but not critical, effect on the qualitative indicators of Sentiment Recognition.

show abstract

The algorithm of building the hierarchical contextual framework of textual corpora

Cited by 6 publications

References 10 publications

Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations

Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations

Methodology of Constructing and Analyzing the Hierarchical Contextually-Oriented Corpora

Improving the Accuracy in Text Classification Methodology in Light of Modelling the Latent Semantic Relations

Contact Info

Product

Resources

About