Filtering out irrelevant documents and classifying the relevant ones into topical categories is a de facto task in many applications. However, supervised learning solutions require extravagant human efforts on document labeling. In this paper, we propose a novel seed-guided topic model for dataless short text classification and filtering, named SSCF. Without using any labeled documents, SSCF takes a few “seed words” for each category of interest, and conducts short text filtering and classification in a weakly supervised manner. To overcome the issues of data sparsity and imbalance, the short text collection is mapped to a collection of pseudodocuments, one for each word. SSCF infers two kinds of topics on pseudo-documents: category-topics and general-topics. Each category-topic is associated with one category of interest, covering the meaning of the latter. In SSCF, we devise a novel word relevance estimation process based on the seed words, for hidden topic inference. The dominating topic of a short text is identified through post inference and then used for filtering and classification. On two real-world datasets in two languages, experimental results show that our proposed SSCF consistently achieves better classification accuracy than state-of-the-art baselines. We also observe that SSCF can even achieve superior performance than the supervised classifiers supervised latent dirichlet allocation (sLDA) and support vector machine (SVM) on some testing tasks.
Yukun Zheng, Yiqun Liu, Zhen Fan, Cheng Luo, Qingyao Ai, Min Zhang and Shaoping Ma
A number of deep neural networks have been proposed to improve the performance of document ranking in information retrieval studies. However, the training processes of these models usually need a large scale of labeled data, leading to data shortage becoming a major hindrance to the improvement of neural ranking models’ performances. Recently, several weakly supervised methods have been proposed to address this challenge with the help of heuristics or users’ interaction in the Search Engine Result Pages (SERPs) to generate weak relevance labels. In this work, we adopt two kinds of weakly supervised relevance, BM25-based relevance and click model-based relevance, and make a deep investigation into their differences in the training of neural ranking models. Experimental results show that BM25-based relevance helps models capture more exact matching signals, while click model-based relevance enhances the rankings of documents that may be preferred by users. We further proposed a cascade ranking framework to combine the two weakly supervised relevance, which significantly promotes the ranking performance of neural ranking models and outperforms the best result in the last NTCIR-13 We Want Web (WWW) task. This work reveals the potential of constructing better document retrieval systems based on multiple kinds of weak relevance signals.
The study aims to reveal the role of social media and its influence on information sharing within public organizations and emphasis on the distribution affordance to facilitate information processes. Existing literature emphasized different aspects of social media in the public sector to promote the relationship between government and citizens or provide better public service, for example, innovation, policies, openness, and communication. However, there is a wide gap in the literature to investigate social media use and information sharing within public organizations. The current study tries to accomplish the goal by conducting semi-structured interviews with 15 employees in public organizations in Chaohu city, China and applying content analysis on the interviews. Despite the existing literature, the targeted group for this study is divided into three levels (i) senior-level, (ii) middle-level, and (iii) junior-level employees to get a better view of social media. The study is based on grounded theory for coding analysis. We provide an overview of social media use within Chinese public organizations and discuss five social media affordances involved in the public organizations. Finally, we provide the implications, limitations, recommendation, and future research of this research area.
Danmu function as an augmented comment feature has been adopted by almost all live streaming platforms to foster interaction between viewers and the streamer in China. However, few studies have been conducted to understand the determinants of users’ Danmu sending behavior on live streaming platforms. This study examines this phenomenon from the lens of effectance theory and the S-O-R framework. We propose that two effectances – Danmu effectance and live streaming effectance – play an essential role in active Danmu participation. In addition, we explore the effects of time-enhanced (synchronicity) and space-enhanced technical characteristic (visibility) of Danmu on live streaming platforms on two effectances. Data analysis of 877 participations from Douyu platform in mainland China indicates that active Danmu participation is positively associated with Danmu effectance and live streaming effectance which are influenced by both time-enhanced technical feature (synchronicity) and space-enhanced technical feature (visibility). In addition, the study finds that demographic characteristics, namely education and income, also affect active Danmu participation.
The study presents a new innovative approach to the accepted principle of agile enterprise management by using the method of rationalization of the structure of administrative and office work (DZA). Agile enterprise management focused on minimizing costs induces permanent necessity to look for new methods and techniques to achieve the assumed cost targets. Contemporary enterprises have access to a wide range of activities and instruments affecting the formation of costs while running their business. In connection with the above, a research question was posed in the study; how to implement the concept of agile enterprise management based on methods of rationalization of the structure of administrative and office work and lean management? The aim of the paper is to learn and evaluate the applied method of analysis of run times in the system of administrative and office work (DZA Dürchlaufzeitenanalyse) in the context of agile management of the enterprise. The study indicates the advantages and disadvantages of implementing this concept for the enterprise, thus the paper bridges the gap between theory and practice in the selection of instruments to realize of the concept of agile business management. The applied research method is literature studies and descriptive analysis in the field of application of the method of minimizing time of runs. Descriptive analysis was developed based on an example of the activity of a chemical industry enterprise operating in Poland. The research issues are important and up-to-date due to the constant need to maintain cost discipline in the enterprise and the implementation of innovative approaches to seek ways to reduce costs.
Tourist services represent a category of services in which the inseparability of production and consumption, the inability to be storable, the immateriality, and last but not least non-durability, induces in tourism management a number of peculiarities and difficulties. Under these circumstances the development of medium-term strategies involves long-term studies regarding on the one hand the developments and characteristics of the demand, and on the other hand the tourist potential analysis at regional and local level. Although in the past 20 years there has been tremendous growth of on-line booking made by household users, the tour operators agencies as well as those with sales activity continue to offer the specific services for a large number of tourists, that number, in the case of domestic tourism, increased by 1.6 times in case of the tour operators and by 4.44 times in case of the agencies with sales activity. At the same time, there have been changes in the preferences of tourists regarding their holiday destinations in Romania. Started on these considerations, paper based on a logistic model, examines the evolution of the probabilities and scores corresponding to the way the Romanian tourists spend their holidays on the types of tourism agencies, actions and tourist areas in Romania.
Assess the performance of a patrimonial entity, its financial position and its change, the degree of risk in an economic and financial environment - socially dynamic, requires information far beyond the scope of financial-accounting information. Therefore, it is necessary to complete the financial data provided by the financial statements with the information on the technical and human potential (equipment quality, modernization, qualification of employees, level of labor productivity, etc.), commercial potential (quality of products / services and distribution network, price level, etc.), the intensity of competition, the position of the entity on the market, the image of the entity and its products / services, etc. All this information can be synthesized on responsibility boards (technical and production, human resources, trade-supply / sales / marketing, etc.) in a dashboard, which is a synoptic, legible and interpretable instrument, carried out with a certain frequency, which highlights the significant deviations between the results achieved and the fixed objectives, in order to ensure the necessary corrections for the good performance of the activity. This communication aims to highlight the results of the research on the importance of the dashboard as a control and pilotage tool for Romanian patrimonial entities.
Akinyemi A. Ajibola, Muideen A. Isiaka, Ikenna T. Nnoli and Christiana A. Abimbola
The study examined the impact of electricity supply on economic diversification in Nigeria, using time series data from 1981 to 2016. The study employed descriptive analysis and Autoregressive Distributed Lag (ARDL) techniques. The Augmented Dickey-Fuller unit root test showed that the variables are integrated of different orders.
The result from the Bounds co-integration test to show the presence of a long-run relationship among the variables was inconclusive. The short run (ARDL) model, however, indicated a positive insignificant relationship between electricity supply and economic diversification in Nigeria. The findings of the study revealed that the electricity supply had not played a fundamental role in enhancing economic diversification in Nigeria.
The study, therefore, recommended that for Nigeria to drive economic diversification through electricity supply, the government should fix the electricity supply problem which can be achieved by short-term action to reduce technical faults through maintenance of the transmission and distribution infrastructure or long-term interventions to expand generating capacity.
Olukayode E. Maku, Emmanuel O. Ajike and Solomon Chinedu
While developed and most developing nations have seen the need and continue to invest heavily in the development and training of her manpower as shown by huge budgetary allocations to education and health, Nigeria continues to play politics with her human capital development policy which has been poor and only been effective on paper despite the huge outlay of human capital available at our disposal. This study therefore examined the impact of human capital development on the macroeconomic performance of Nigeria. Using autoregressive distributed lagged model, the study proxied human capital development using government expenditure on education, government expenditure on health, secondary school enrolment rate, and school enrolment rate at tertiary level, while per capita GDP was used as proxy variable for measuring macroeconomic performance.
The results of the estimated short and long run ARDL models indicated, an insignificant and negative relationship between human capital development and gross domestic product per capita (GDPPC) in the short run. Another result of this study is that, only tertiary enrolment rate (TER) has a significant and positive impact on gross domestic product per capita (GDPPC). This finding was an indication of relatively good but insufficient efforts by government to boost human capital. The study concluded that while human capital development is crucial for accelerated macroeconomic performance, government efforts aimed at boosting human capital has had a depressing effect on macroeconomic performance. On the strength of this, the study recommended that government and economic policy makers in Nigeria should place greater emphasis on human capital development.