Self-training from labeled features for sentiment analysis

Sentiment analysis concerns about automatically identifying sentiment or opinion expressed in a given piece of text. Most prior work either use prior lexical knowledge defined as sentiment polarity of words or view the task as a text classification problem and rely on labeled corpora to train a sentiment classifier. While lexicon-based approaches do not adapt well to different domains, corpus-based approaches require expensive manual annotation effort. In this paper, we propose a novel framework where an initial classifier is learned by incorporating prior information extracted from an existing sentiment lexicon with preferences on expectations of sentiment labels of those lexicon words being expressed using generalized expectation criteria. Documents classified with high confidence are then used as pseudo-labeled examples for automatical domain-specific feature acquisition. The word-class distributions of such self-learned features are estimated from the pseudo-labeled examples and are used to train another classifier by constraining the model's predictions on unlabeled instances. Experiments on both the movie-review data and the multi-domain sentiment dataset show that our approach attains comparable or better performance than existing weakly-supervised sentiment classification methods despite using no labeled documents.

Biomedical events extraction using the hidden vector state model

Objective: Biomedical events extraction concerns about events describing changes on the state of bio-molecules from literature. Comparing to the protein-protein interactions (PPIs) extraction task which often only involves the extraction of binary relations between two proteins, biomedical events extraction is much harder since it needs to deal with complex events consisting of embedded or hierarchical relations among proteins, events, and their textual triggers. In this paper, we propose an information extraction system based on the hidden vector state (HVS) model, called HVS-BioEvent, for biomedical events extraction, and investigate its capability in extracting complex events. Methods and material: HVS has been previously employed for extracting PPIs. In HVS-BioEvent, we propose an automated way to generate abstract annotations for HVS training and further propose novel machine learning approaches for event trigger words identification, and for biomedical events extraction from the HVS parse results. Results: Our proposed system achieves an F-score of 49.57% on the corpus used in the BioNLP'09 shared task, which is only 2.38% lower than the best performing system by UTurku in the BioNLP'09 shared task. Nevertheless, HVS-BioEvent outperforms UTurku's system on complex events extraction with 36.57% vs. 30.52% being achieved for extracting regulation events, and 40.61% vs. 38.99% for negative regulation events. Conclusions: The results suggest that the HVS model with the hierarchical hidden state structure is indeed more suitable for complex event extraction since it could naturally model embedded structural context in sentences.

A novel framework of training hidden Markov support vector machines from lightly-annotated data

Natural language understanding (NLU) aims to map sentences to their semantic mean representations. Statistical approaches to NLU normally require fully-annotated training data where each sentence is paired with its word-level semantic annotations. In this paper, we propose a novel learning framework which trains the Hidden Markov Support Vector Machines (HM-SVMs) without the use of expensive fully-annotated data. In particular, our learning approach takes as input a training set of sentences labeled with abstract semantic annotations encoding underlying embedded structural relations and automatically induces derivation rules that map sentences to their semantic meaning representations. The proposed approach has been tested on the DARPA Communicator Data and achieved 93.18% in F-measure, which outperforms the previously proposed approaches of training the hidden vector state model or conditional random fields from unaligned data, with a relative error reduction rate of 43.3% and 10.6% being achieved.

Joint sentiment/topic model for sentiment analysis

Sentiment analysis or opinion mining aims to use automated tools to detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework based on Latent Dirichlet Allocation (LDA), called joint sentiment/topic model (JST), which detects sentiment and topic simultaneously from text. Unlike other machine learning approaches to sentiment classification which often require labeled corpora for classifier training, the proposed JST model is fully unsupervised. The model has been evaluated on the movie review dataset to classify the review sentiment polarity and minimum prior information have also been explored to further improve the sentiment classification accuracy. Preliminary experiments have shown promising results achieved by JST.

Data envelopment analysis model for the appraisal and relative performance evaluation of nurses at an intensive care unit

The appraisal and relative performance evaluation of nurses are very important and beneficial for both nurses and employers in an era of clinical governance, increased accountability and high standards of health care services. They enhance and consolidate the knowledge and practical skills of nurses by identification of training and career development plans as well as improvement in health care quality services, increase in job satisfaction and use of cost-effective resources. In this paper, a data envelopment analysis (DEA) model is proposed for the appraisal and relative performance evaluation of nurses. The model is validated on thirty-two nurses working at an Intensive Care Unit (ICU) at one of the most recognized hospitals in Lebanon. The DEA was able to classify nurses into efficient and inefficient ones. The set of efficient nurses was used to establish an internal best practice benchmark to project career development plans for improving the performance of other inefficient nurses. The DEA result confirmed the ranking of some nurses and highlighted injustice in other cases that were produced by the currently practiced appraisal system. Further, the DEA model is shown to be an effective talent management and motivational tool as it can provide clear managerial plans related to promoting, training and development activities from the perspective of nurses, hence increasing their satisfaction, motivation and acceptance of appraisal results. Due to such features, the model is currently being considered for implementation at ICU. Finally, the ratio of the number DEA units to the number of input/output measures is revisited with new suggested values on its upper and lower limits depending on the type of DEA models and the desired number of efficient units from a managerial perspective.

A weakly-supervised Bayesian model for violence detection from social media

Social streams have proven to be the mostup-to-date and inclusive information on cur-rent events. In this paper we propose a novelprobabilistic modelling framework, called violence detection model (VDM), which enables the identification of text containing violent content and extraction of violence-related topics over social media data. The proposed VDM model does not require any labeled corpora for training, instead, it only needs the in-corporation of word prior knowledge which captures whether a word indicates violence or not. We propose a novel approach of deriving word prior knowledge using the relative entropy measurement of words based on the in-tuition that low entropy words are indicative of semantically coherent topics and therefore more informative, while high entropy words indicates words whose usage is more topical diverse and therefore less informative. Our proposed VDM model has been evaluated on the TREC Microblog 2011 dataset to identify topics related to violence. Experimental results show that deriving word priors using our proposed relative entropy method is more effective than the widely-used information gain method. Moreover, VDM gives higher violence classification results and produces more coherent violence-related topics compared toa few competitive baselines.

A fuzzy decision tree-based duration model for Standard Yorùbá text-to-speech synthesis

In this paper, we present syllable-based duration modelling in the context of a prosody model for Standard Yorùbá (SY) text-to-speech (TTS) synthesis applications. Our prosody model is conceptualised around a modular holistic framework. This framework is implemented using the Relational Tree (R-Tree) techniques. An important feature of our R-Tree framework is its flexibility in that it facilitates the independent implementation of the different dimensions of prosody, i.e. duration, intonation, and intensity, using different techniques and their subsequent integration. We applied the Fuzzy Decision Tree (FDT) technique to model the duration dimension. In order to evaluate the effectiveness of FDT in duration modelling, we have also developed a Classification And Regression Tree (CART) based duration model using the same speech data. Each of these models was integrated into our R-Tree based prosody model. We performed both quantitative (i.e. Root Mean Square Error (RMSE) and Correlation (Corr)) and qualitative (i.e. intelligibility and naturalness) evaluations on the two duration models. The results show that CART models the training data more accurately than FDT. The FDT model, however, shows a better ability to extrapolate from the training data since it achieved a better accuracy for the test data set. Our qualitative evaluation results show that our FDT model produces synthesised speech that is perceived to be more natural than our CART model. In addition, we also observed that the expressiveness of FDT is much better than that of CART. That is because the representation in FDT is not restricted to a set of piece-wise or discrete constant approximation. We, therefore, conclude that the FDT approach is a practical approach for duration modelling in SY TTS applications. © 2006 Elsevier Ltd. All rights reserved.

Representing the assessment process for psychodynamic psychotherapy within a computerized model of human classification

This research describes a computerized model of human classification which has been constructed to represent the process by which assessments are made for psychodynamic psychotherapy. The model assigns membership grades (MGs) to clients so that the most suitable ones have high values in the therapy category. Categories consist of a hierarchy of components, one of which, ego strength, is analysed in detail to demonstrate the way it has captured the psychotherapist's knowledge. The bottom of the hierarchy represents the measurable factors being assessed during an interview. A questionnaire was created to gather the identified information and was completed by the psychotherapist after each assessment. The results were fed into the computerized model, demonstrating a high correlation between the model MGs and the suitability ratings of the psychotherapist (r = .825 for 24 clients). The model has successfully identified the relevant data involved in assessment and simulated the decision-making process of the expert. Its cognitive validity enables decisions to be explained, which means that it has potential for therapist training and also for enhancing the referral process, with benefits in cost effectiveness as well as in the reduction of trauma to clients. An adapted version measuring client improvement would give quantitative evidence for the benefit of therapy, thereby supporting auditing and accountability. © 1997 The British Psychological Society.

Laser-induced breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model

Abstract A new LIBS quantitative analysis method based on analytical line adaptive selection and Relevance Vector Machine (RVM) regression model is proposed. First, a scheme of adaptively selecting analytical line is put forward in order to overcome the drawback of high dependency on a priori knowledge. The candidate analytical lines are automatically selected based on the built-in characteristics of spectral lines, such as spectral intensity, wavelength and width at half height. The analytical lines which will be used as input variables of regression model are determined adaptively according to the samples for both training and testing. Second, an LIBS quantitative analysis method based on RVM is presented. The intensities of analytical lines and the elemental concentrations of certified standard samples are used to train the RVM regression model. The predicted elemental concentration analysis results will be given with a form of confidence interval of probabilistic distribution, which is helpful for evaluating the uncertainness contained in the measured spectra. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples have been carried out. The multiple correlation coefficient of the prediction was up to 98.85%, and the average relative error of the prediction was 4.01%. The experiment results showed that the proposed LIBS quantitative analysis method achieved better prediction accuracy and better modeling robustness compared with the methods based on partial least squares regression, artificial neural network and standard support vector machine.

Probabilistic multiple model neural network based leak detection system:experimental study

This paper presents an effective decision making system for leak detection based on multiple generalized linear models and clustering techniques. The training data for the proposed decision system is obtained by setting up an experimental pipeline fully operational distribution system. The system is also equipped with data logging for three variables; namely, inlet pressure, outlet pressure, and outlet flow. The experimental setup is designed such that multi-operational conditions of the distribution system, including multi pressure and multi flow can be obtained. We then statistically tested and showed that pressure and flow variables can be used as signature of leak under the designed multi-operational conditions. It is then shown that the detection of leakages based on the training and testing of the proposed multi model decision system with pre data clustering, under multi operational conditions produces better recognition rates in comparison to the training based on the single model approach. This decision system is then equipped with the estimation of confidence limits and a method is proposed for using these confidence limits for obtaining more robust leakage recognition results.

Improved Hybrid Model of HMM/GMM for Speech Recognition

In this paper, we propose a speech recognition engine using hybrid model of Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM). Both the models have been trained independently and the respective likelihood values have been considered jointly and input to a decision logic which provides net likelihood as the output. This hybrid model has been compared with the HMM model. Training and testing has been done by using a database of 20 Hindi words spoken by 80 different speakers. Recognition rates achieved by normal HMM are 83.5% and it gets increased to 85% by using the hybrid approach of HMM and GMM.

TQM in e-Learning: a Self-assessment Model and Questionnaire

Organizations are seeking new, integrated systems that enable rapid changes through early identification of opportunities and problems, tracking of progress against plans, flexible allocation of resources to achieve goals, and consistent operations. Total Quality Management (TQM) is an overall business strategy. It means that all activities of the company will be focused on satisfying all stakeholders of the company. TQM can be realised by using the EFQM model. The EFQM model is a tool that organizations may use as a framework for self-evaluation that enables an organization to identify its strengths and areas for improvement and the extent to which its operations and results are in line with the characteristics of an excellent organization. We focus on a training organisation or to the learning department of an organization. So we are limiting the EFQM model to the training /learning activities. We can apply EFQM perfect on the level of an activity (business line) of a company. We selected the main criteria for which the learner can play the role of assessor. So only three main criteria left: the enabling resources, the enabling processes and the (learning) results for the learner. We limited the last one to “learning results” based on the Kirkpatrick model.

The Conception of Creation of Integrated Development Environment for Computer Training Systems

The various questions of creation of integrated development environment for computer training systems are considered in the given paper. The information technologies that can be used for creation of the integrated development environment are described. The different didactic aspects of realization of such systems are analyzed. The ways to improve the efficiency and quality of learning process with computer training systems for distance education are pointed.

A Didactic Model of Computer Supported Education in Higher Mathematics

Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, May, 2016

Towards a multilevel model of the high performance work systems–workplace safety relationship

Human Resource (HR) systems and practices generally referred to as High Performance Work Practices (HPWPs), (Huselid, 1995) (sometimes termed High Commitment Work Practices or High Involvement Work Practices) have attracted much research attention in past decades. Although many conceptualizations of the construct have been proposed, there is general agreement that HPWPs encompass a bundle or set of HR practices including sophisticated staffing, intensive training and development, incentive-based compensation, performance management, initiatives aimed at increasing employee participation and involvement, job safety and security, and work design (e.g. Pfeffer, 1998). It is argued that these practices either directly and indirectly influence the extent to which employees’ knowledge, skills, abilities, and other characteristics are utilized in the organization. Research spanning nearly 20 years has provided considerable empirical evidence for relationships between HPWPs and various measures of performance including increased productivity, improved customer service, and reduced turnover (e.g. Guthrie, 2001; Belt & Giles, 2009). With the exception of a few papers (e.g., Laursen &Foss, 2003), this literature appears to lack focus on how HPWPs influence or foster more innovative-related attitudes and behaviours, extra role behaviors, and performance. This situation exists despite the vast evidence demonstrating the importance of innovation, proactivity, and creativity in its various forms to individual, group, and organizational performance outcomes. Several pertinent issues arise when considering HPWPs and their relationship to innovation and performance outcomes. At a broad level is the issue of which HPWPs are related to which innovation-related variables. Another issue not well identified in research relates to employees’ perceptions of HPWPs: does an employee actually perceive the HPWP –outcomes relationship? No matter how well HPWPs are designed, if they are not perceived and experienced by employees to be effective or worthwhile then their likely success in achieving positive outcomes is limited. At another level, research needs to consider the mechanisms through which HPWPs influence –innovation and performance. The research question here relates to what possible mediating variables are important to the success or failure of HPWPs in impacting innovative behaviours and attitudes and what are the potential process considerations? These questions call for theory refinement and the development of more comprehensive models of the HPWP-innovation/performance relationship that include intermediate linkages and boundary conditions (Ferris, Hochwarter, Buckley, Harrell-Cook, & Frink, 1999). While there are many calls for this type of research to be made a high priority, to date, researchers have made few inroads into answering these questions. This symposium brings together researchers from Australia, Europe, Asia and Africa to examine these various questions relating to the HPWP-innovation-performance relationship. Each paper discusses a HPWP and potential variables that can facilitate or hinder the effects of these practices on innovation- and performance- related outcomes. The first paper by Johnston and Becker explores the HPWPs in relation to work design in a disaster response organization that shifts quickly from business as usual to rapid response. The researchers examine how the enactment of the organizational response is devolved to groups and individuals. Moreover, they assess motivational characteristics that exist in dual work designs (normal operations and periods of disaster activation) and the implications for innovation. The second paper by Jørgensen reports the results of an investigation into training and development practices and innovative work behaviors (IWBs) in Danish organizations. Research on how to design and implement training and development initiatives to support IWBs and innovation in general is surprisingly scant and often vague. This research investigates the mechanisms by which training and development initiatives influence employee behaviors associated with innovation, and provides insights into how training and development can be used effectively by firms to attract and retain valuable human capital in knowledge-intensive firms. The next two papers in this symposium consider the role of employee perceptions of HPWPs and their relationships to innovation-related variables and performance. First, Bish and Newton examine perceptions of the characteristics and awareness of occupational health and safety (OHS) practices and their relationship to individual level adaptability and proactivity in an Australian public service organization. The authors explore the role of perceived supportive and visionary leadership and its impact on the OHS policy-adaptability/proactivity relationship. The study highlights the positive main effects of awareness and characteristics of OHS polices, and supportive and visionary leadership on individual adaptability and proactivity. It also highlights the important moderating effects of leadership in the OHS policy-adaptability/proactivity relationship. Okhawere and Davis present a conceptual model developed for a Nigerian study in the safety-critical oil and gas industry that takes a multi-level approach to the HPWP-safety relationship. Adopting a social exchange perspective, they propose that at the organizational level, organizational climate for safety mediates the relationship between enacted HPWS’s and organizational safety performance (prescribed and extra role performance). At the individual level, the experience of HPWP impacts on individual behaviors and attitudes in organizations, here operationalized as safety knowledge, skills and motivation, and these influence individual safety performance. However these latter relationships are moderated by organizational climate for safety. A positive organizational climate for safety strengthens the relationship between individual safety behaviors and attitudes and individual-level safety performance, therefore suggesting a cross-level boundary condition. The model includes both safety performance (behaviors) and organizational level safety outcomes, operationalized as accidents, injuries, and fatalities. The final paper of this symposium by Zhang and Liu explores leader development and relationship between transformational leadership and employee creativity and innovation in China. The authors further develop a model that incorporates the effects of extrinsic motivation (pay for performance: PFP) and employee collectivism in the leader-employee creativity relationship. The papers’ contributions include the incorporation of a PFP effect on creativity as moderator, rather than predictor in most studies; the exploration of the PFP effect from both fairness and strength perspectives; the advancement of knowledge on the impact of collectivism on the leader- employee creativity link. Last, this is the first study to examine three-way interactional effects among leader-member exchange (LMX), PFP and collectivism, thus, enriches our understanding of promoting employee creativity. In conclusion, this symposium draws upon the findings of four empirical studies and one conceptual study to provide an insight into understanding how different variables facilitate or potentially hinder the influence various HPWPs on innovation and performance. We will propose a number of questions for further consideration and discussion. The symposium will address the Conference Theme of ‘Capitalism in Question' by highlighting how HPWPs can promote financial health and performance of organizations while maintaining a high level of regard and respect for employees and organizational stakeholders. Furthermore, the focus on different countries and cultures explores the overall research question in relation to different modes or stages of development of capitalism.