Applying the Som Model to Text Classification According to Register and Stylistic Content

Tambouratzis, George; Hairetakis, Nikolaos; Μαρκαντωνάτου, Στέλλα; Carayannis, G.

doi:10.1142/s0129065703001352

Cited by 15 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, LSI consumes ample time in calculating similarities of new queries against all documents, but a SOM only needs to calculate similarities versus some representative subset of old input data and can then map new input straight onto the most similar models without having to recompute the whole mapping. Tambouratzis et al (2003) use SOMs for categorizing texts according to register and author style, and show that the results are compatible to those generated by statistical methods.…”

Section: Self-organizing Mapssupporting

confidence: 61%

Classifying Amharic webnews

et al. 2009

View full text Add to dashboard Cite

We present work aimed at compiling an Amharic corpus from the Web and automatically categorizing the texts. Amharic is the second most spoken Semitic language in the World (after Arabic) and used for countrywide communication in Ethiopia. It is highly inflectional and quite dialectally diversified. We discuss the issues of compiling and annotating a corpus of Amharic news articles from the Web. This corpus was then used in three sets of text classification experiments. Working with a less-researched language highlights a number of practical issues that might otherwise receive less attention or go unnoticed. The purpose of the experiments has not primarily been to develop a cuttingedge text classification system for Amharic, but rather to put the spotlight on some of these issues. The first two sets of experiments investigated the use of Self-Organizing Maps (SOMs) for document classification. Testing on small datasets, we first looked at classifying unseen data into 10 predefined categories of news items, and then at clustering it around query content, when taking 16 queries as class labels. The second set of experiments investigated the effect of operations such as stemming and part-of-speech tagging on text classification performance. We compared three representations while constructing classification models based on bagging of decision trees for the 10 predefined news categories. The best accuracy was achieved using the full text as representation. A representation using only the nouns performed almost equally well, confirming the assumption that most of the information required for distinguishing between various categories actually is contained in the nouns, while stemming did not have much effect on the performance of the classifier.

show abstract

Section: Self-organizing Mapssupporting

confidence: 61%

Classifying Amharic webnews

et al. 2009

View full text Add to dashboard Cite

show abstract

“…It is claimed that if sufficient differences exist between the manner in which different authors express themselves, the SOM should retrieve such differences even though it is not provided with information about the actual authorship of the documents. Indeed, preliminary results reviewed in the next two sections have indicated that author characteristics can be detected by the SOM in data-mining experiments [11]. Here, the emphasis is placed on confirming these results using more extensive datasets and determining the extent to which each of the feature categories contributes to the discrimination between the authors via the SOM.…”

Section: Som Neural Networkmentioning

confidence: 89%

“…In these studies, originally statistical methods were used [9], [10], since they possessed solid theoretical foundations for the classification tasks at hand and, being supervised, were expected to provide the highest possible classification accuracy. Following that, SOM-based techniques were evaluated in the same tasks, in order to indicate the effectiveness of biologically inspired unsupervised methods in this task [11]. It has been found that using both the SOM and classical statistical techniques, the separation of registers is easier than the separation of documents belonging to the same register according to their author's style.…”

Section: Introductionmentioning

confidence: 99%

Assessing the effectiveness of feature groups in author recognition tasks with the SOM model

Tambouratzis

2006

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

The present paper focuses on studying the effectiveness of the self-organizing map (SOM) when applied to the task of categorizing a corpus of texts according to the style of their authors. This task is of particular importance for information retrieval applications using very large databases of documents. The emphasis of this article is to determine the extent to which the SOM possesses the ability to analyze such data, successfully uncovering the stylistic differences among authors in an unsupervised manner. To that end, a variety of feature vectors are studied, each of which either 1) comprises a single category of linguistic features or 2) spans several different categories of linguistic features, in order to determine the effectiveness of each feature category. It is shown that the highest accuracy is achieved when using a vector covering multiple linguistic categories. A comparison of the results obtained to the results of statistical methods indicates the ability of the SOM network to reveal the clustering potential of isolated parameter groups and its effectiveness in handling efficiently high-dimensional data vectors. Potential extensions to related text-organization techniques, such as the WEBSOM, thus become evident.

show abstract

“…Details on the semi-automatic featureselection process are provided in [1] [2]. The features were counted in a completely automated manner and can be distinguished into the following main groups:…”

Section: B Features Countedmentioning

confidence: 99%

Neural Networks for Author Attribution

Tsimboukakis

Tambouratzis

2007

2007 IEEE International Fuzzy Systems Conference

Self Cite

View full text Add to dashboard Cite

The present article investigates the effectiveness of neural network models when applied to the task of categorising texts in the Greek language based on the style of their authors. Multilayer perceptrons (MLP), Radial Basis Function networks (RBF) and Self-Organizing Maps (SOM) are comparatively studied on the task of classifying documents based on a set of countable stylistic features. This task is of particular importance for information retrieval applications that involve very large databases of documents where the manual classification is extremely labour-intensive.

show abstract

Applying the Som Model to Text Classification According to Register and Stylistic Content

Cited by 15 publications

References 9 publications

Classifying Amharic webnews

Classifying Amharic webnews

Assessing the effectiveness of feature groups in author recognition tasks with the SOM model

Neural Networks for Author Attribution

Contact Info

Product

Resources

About