4,425 Hits in 7.3 sec

State of the Art in Authorship Attribution With Impact Analysis of Stylometric Features on Style Breach Prediction

Rajesh Shardanand Prasad, Midhun Chakkaravarthy
2022 Journal of Cases on Information Technology  
The outcomes of this study can by deployed for dialectology analysis and corpus linguistics, stylistics, natural language processing, classification, and literary and historical analysis, forensic analysis  ...  The reference material contributes robust classifiers with reasonable array of feature extraction techniques, such as Dirichlet–multinomial change point regression to extract the progress of inscription  ...  The noteworthy contribution involves application of social network of the authors and the content of the paper in the settings of dimensionality reduction and topic modelling.  ... 
doi:10.4018/jcit.296716 fatcat:5i6sb6od5bafvdrv4ly5vpz46u

Towards Careful Practices for Automated Linguistic Analysis of Group Learning

Iris Howley, Carolyn Penstein Rosé
2016 Journal of Learning Analytics  
This article explores the capability of multi-dimensional frameworks for analysis of collaborative processes to isolate and assess these separate dimensions of collaboration.  ...  The multifaceted nature of collaborative learning environments necessitates theory to investigate the cognitive, motivational, and relational dimensions of collaboration.  ...  SouFLé 1 is a three-dimensional categorical coding scheme, including a cognitive, motivational, and relational dimension.  ... 
doi:10.18608/jla.2016.33.12 fatcat:oxxqmyph2rdwtisiqnpdgnf6ra

A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data

Rie Kubota Ando, Tong Zhang
2005 Journal of machine learning research  
Under this framework, algorithms for structural learning will be proposed, and computational issues will be investigated.  ...  Acknowledgments The authors would like to thank Trevor Hastie and Robert Tibshirani for helpful discussions and for pointing out related statistical studies.  ...  For text data, some words or linguistic usages will have similar meanings.  ... 
dblp:journals/jmlr/AndoZ05 fatcat:xrg7y4le2vhg7fj5etyqpz3cue

Celebrity profiling through linguistic analysis of digital social networks

Luis G. Moreno-Sandoval, Alexandra Pomares-Quimbaya, Jorge A. Alvarado-Valencia
2021 Computational Social Networks  
This paper proposes a model of feature selection for the classification of celebrities profiles based on their use of a digital social network Twitter.  ...  As a result, extracted features from linguistic cues improved the performance of predictive models of Fame and Gender and facilitate explanations of the model results.  ...  Finally, Fig. 8 used a "FactoMineR" package [75] through the MCA command for categorical variables In contrast, the model for classification shown in Tables 28, 29, 30, 31 was made with Python 3.7  ... 
doi:10.1186/s40649-021-00097-w fatcat:wvg76w2s2vfvhnymi7ravtzuou

Neural Multi-Task Learning for Citation Function and Provenance [article]

Xuan Su, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama
2019 arXiv   pre-print
Given a citation, the former task determines its rhetorical role, while the latter locates the text in the cited paper that contains the relevant cited information.  ...  For both tasks, we show that a single-layer convolutional neural network (CNN) outperforms existing state-of-the-art baselines.  ...  We include instances with these selected linguistic cues into our dataset for annotation.  ... 
arXiv:1811.07351v2 fatcat:q6kwdd4lhjdrpmh46esaoki7vi

From Spin to Swindle: Identifying Falsification in Financial Text

Saliha Minhas, Amir Hussain
2016 Cognitive Computation  
For the first time, this new interdisciplinary research extracts features for readability at a much deeper level, attempts to draw out collocations using n-grams and measures tone using appropriate financial  ...  Separately each of these three sets of features is put through a suite of classification algorithms, to determine classifier performance in this binary fraud/ non-fraud discrimination task.  ...  Additional informed consent was obtained from all patients for which identifying information is included in this article.  ... 
doi:10.1007/s12559-016-9413-9 pmid:27563359 pmcid:PMC4981627 fatcat:xr3nu4fg3jaspc3uyblqcjqk4m

Assessing Parkinson's Disease at Scale Using Telephone-Recorded Speech: Insights from the Parkinson's Voice Initiative

Siddharth Arora, Athanasios Tsanas
2021 Diagnostics  
Using robust feature selection methods we selected 27 dysphonia measures to present into a radial-basis-function support vector machine and demonstrated differentiation of PD participants from controls  ...  Given that this is a highly unbalanced problem, we used the following strategy: we selected a balanced subset (n = 3000 samples) for training and testing using 10-fold cross-validation (CV), and the remaining  ...  Acknowledgments: We are grateful to Aculab for the use of their servers to facilitate data collection. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/diagnostics11101892 pmid:34679590 fatcat:gbkjyrcjjnbrnfdoogqbovaux4

A survey on information visualization: recent advances and challenges

Shixia Liu, Weiwei Cui, Yingcai Wu, Mengchen Liu
2014 The Visual Computer  
At the conclusion of this survey, we identify existing technical challenges and propose directions for future research.  ...  In feature-based text visualization, a feature indicates a non-overlapping text chunk (e.g., keywords or phrases) or a grammatical structure (e.g., infinitives or clauses), inside a document.  ...  Visualization of static textual information The visualization work on static text information can be classified into two categories: feature-based text visualization and topic-based text visualization.  ... 
doi:10.1007/s00371-013-0892-3 fatcat:k2y4xrmffzghvldzn6fg2tkjqi

Topic models do not model topics: epistemological remarks and steps towards best practices

Anna Shadrova
2021 Journal of Data Mining and Digital Humanities  
This paper adds epistemological concerns centering around the interface between topic modeling and linguistic concepts and the argumentative embedding of evidence obtained through topic modeling.  ...  These features are intrinsic and make the interpretation of its results prone to apophenia (the human tendency to perceive random sets of elements as meaningful patterns) and confirmation bias (the human  ...  dimensionality reduction.  ... 
doi:10.46298/jdmdh.7595 fatcat:fzld7ocuvfam5drk2ofbhtdame

What is technical text?

Terry Copeck, Ken Barker, Sylvain Delisle, Stan Szpakowicz, Jean-François Delannoy
1997 Language Sciences  
Belkacem Abdous in the Département de mathématiques et d'informatique at the Université du Québec à Trois-Rivières for his guidance on statistical analysis; Chris Drummond for reading and commenting on  ...  These authors concentrated on automatability, selecting only features which are easy to compute in a mechanical way for a given text.  ...  Identify a set of linguistic features likely to serve as discriminators for different varieties; 4. Count the number of occurrences of each linguistic feature in each text sample; 5.  ... 
doi:10.1016/s0388-0001(97)00003-x fatcat:xt7xabf37bhmrnxqthdsxx5tkm

Using Negation and Phrases in Inducing Rules for Text Classification [chapter]

Stephanie Chua, Frans Coenen, Grant Malcolm, Matías Fernando, García Constantino
2011 Research and Development in Intelligent Systems XXVIII  
An investigation into the use of negation in Inductive Rule Learning (IRL) for text classification is described.  ...  include large numbers of features such as those used in text mining applications.  ...  In our experiments, despite a rigorous reduction factor of 0.9 (using only 10% of the features), global feature selection methods are still computationally expensive.  ... 
doi:10.1007/978-1-4471-2318-7_11 dblp:conf/sgai/ChuaCMG11 fatcat:uziw3nqwkjcaxpxwzzkhgferj4

From Distributional Semantics to Conceptual Spaces: A Novel Computational Method for Concept Creation

Stephen McGregor, Kat Agres, Matthew Purver, Geraint A. Wiggins
2015 Journal of Artificial General Intelligence  
select characteristic dimensions associated with seed terms, and thus a subspace of terms defining the related concept.  ...  We define a computational method for discovering members of concepts based on semantic spaces: starting with a standard distributional model derived from corpus co-occurrence statistics, we dynamically  ...  of dimensional reduction.  ... 
doi:10.1515/jagi-2015-0004 fatcat:tzlwuogvnjchxd6dufotsw6rhy

Deep learning: from speech recognition to language and multimodal processing

Li Deng
2016 APSIPA Transactions on Signal and Information Processing  
Next, more challenging applications of deep learning, natural language and multimodal processing, are selectively reviewed and analyzed.  ...  Finally, a number of key issues in deep learning are discussed, and future directions are analyzed for perceptual tasks such as speech, image, and video, as well as for cognitive tasks involving natural  ...  That is, each linguistic entity (e.g. word, phrase, sentence, paragraph, or a full text document), a physical entity, a person, a concept, or a relation, which is often represented as a sparse, high-dimensional  ... 
doi:10.1017/atsip.2015.22 fatcat:rsaafhsbfzeo3l6dxycjewcmi4

Rough Set Feature Selection Algorithms for Textual Case-Based Classification [chapter]

Kalyan Moy Gupta, David W. Aha, Philip Moore
2006 Lecture Notes in Computer Science  
Feature selection algorithms can reduce the high dimensionality of textual cases and increase case-based task performance.  ...  Rough set feature selection algoritms for textual case-based classification.  ...  ., 2005) , we introduced RST motivated feature selection algorithms for a multi-class classification task.  ... 
doi:10.1007/11805816_14 fatcat:rcperkbtqrfktfcglwcocm3nlu

Detecting contrast patterns in newspaper articles by combining discourse analysis and text mining

Senja Pollak, Roel Coesemans, Walter Daelemans, Nada Lavrač
2011 Pragmatics: Quarterly Publication of the International Pragmatics Association  
It illustrates how text mining methods can assist discourse analysis by finding contrast patterns which provide evidence for ideological differences between local and international press coverage.  ...  Text mining aims at constructing classification models and finding interesting patterns in large text collections.  ...  He has coordinated or participated in several national and European projects on text mining and computational linguistics, and is (co-)author of several publications in these areas, among others of a monograph  ... 
doi:10.1075/prag.21.4.07pol fatcat:d74burpf2bcjpe44s6ase5k6ne
« Previous Showing results 1 — 15 out of 4,425 results