Latent Dirichlet Allocation Algorithm Research Articles

RETRACTED ARTICLE: Multimedia text classification algorithm using potential Dirichlet distribution in mobile cloud computing environment

In order to solve the problem of inaccurate description of news content features and user interest features in mobile cloud computing, proposed a multimedia text classification algorithm that utilizes multi-tag potential Dirichlet distribution. The algorithm is based on the traditional latent Dirichlet allocation (LDA) model and assumes a linear relationship between user tags and potential topics. Therefore, a relational matrix is introduced in the LDA model to describe the corresponding relationship between the tag and the topic, so that the probability distribution of the tag on the word can be inferred from the probability distribution of the topic on the word. The algorithm first learns the probability distribution table of label words by Gibbs sampling method, then infers the probability distribution of new documents on labels according to the model parameters, so as to realize the purpose of predicting the corresponding multiple labels of documents. In order to improve the ability of the algorithm to deal with massive data, the parallel algorithm has been improved. Since the bottleneck of the algorithm lies mainly in the serial nature of global variable updating and communication, the core idea of our parallelization is that in massive text training, global delay updating and asynchronous communication will not affect the final training results. Experiments show that the proposed algorithm has greatly improved the training efficiency. The classification accuracy is higher than that of Naive Bayesian algorithm and Support Vector Machine (SVM) algorithm proposed in other literatures. The average classification accuracy can achieve at about 95%, and it can be used as a general parallel framework of supervised LDA algorithm.

Analyzing the startup ecosystem of India: a Twitter analytics perspective

PurposeThe purpose of this paper is to use Twitter analytics for analyzing the startup ecosystem of India.Design/methodology/approachThe paper uses descriptive analysis and content analytics techniques of social media analytics to examine 53,115 tweets from 15 Indian startups across different industries. The study also employs techniques such as Naïve Bayes Algorithm for sentiment analysis and Latent Dirichlet allocation algorithm for topic modeling of Twitter feeds to generate insights for the startup ecosystem in India.FindingsThe Indian startup ecosystem is inclined toward digital technologies, concerned with people, planet and profit, with resource availability and information as the key to success. The study categorizes the emotions of tweets as positive, neutral and negative. It was found that the Indian startup ecosystem has more positive sentiments than negative sentiments. Topic modeling enables the categorization of the identified keywords into clusters. Also, the study concludes on the note that the future of the Indian startup ecosystem is Digital India.Research limitations/implicationsThe analysis provides a methodology that future researchers can use to extract relevant information from Twitter to investigate any issue.Originality/valueAny attempt to analyze the startup ecosystem of India through social media analysis is limited. This research aims to bridge such a gap and tries to analyze the startup ecosystem of India from the lens of social media platforms like Twitter.

Exploring the Weekly Travel Patterns of Private Vehicles Using Automatic Vehicle Identification Data: A Case Study of Wuhan, China

Automatic vehicle identification (AVI) systems collect 24 h vehicle travel data for the efficient management of traffic flows. The automatic vehicle identification data collected by an overhead traffic monitoring system provides a means for understanding urban traffic flows and human mobility. This article explores the weekly travel patterns of private vehicles based on AVI data in Wuhan, a megacity in Central China. We extracted origin–destination information and applied the K-Means clustering algorithm to classify spatial traffic hot spots by camera locations. Subsequently, the Latent Dirichlet Allocation algorithm was used to mine the temporal travel patterns of individual vehicles. The cluster results are summarized in nine travel probability matrixes. The effectiveness of this approach is illustrated by a case study using a large set of AVI data collected from 19 to 24 November 2018, in Wuhan, China. The results revealed six variations of the travel demand on weekdays and weekends—the commuting behaviors of private drivers triggered a tidal change in traffic flows. This study also exposed nine weekly travel patterns for private cars, reflecting temporal similarities of human mobility patterns. We identified four types of commuters. These results can help city managers understand daily changes in urban travel demands.

A Different Text Mining Process for Classifying Journal Databases using Machine Learning Algorithms

Google is the information repository for the entire world and is an important Search engine used for Information Retrieval. Accessing web pages is getting increased everyday which can be compared to the speed in which light travels. Biggest Challenge is identifying the user interest and providing them information based on the high relevancy. Mostly researchers search journal documents for their research every day. Classifying the content as papers or Slides or thesis is very difficult as the words used in these documents are not semantically checked. To mine the correct content in web page Data Mining is used by most of the researchers. Text Mining is one of its application. Text mining in nutshell is extracting useful information from unstructured data. The proposed Model Author Keyword Weightage in Journal Ranking (AKWJR) is developed to retrieve relevant journals that will help the researchers to identify the relevant documents from the pool of irrelevant documents. In many keyword ranking applications such as RAKE and TEXTRANK author annotated keywords were compared and used for ranking. The assignment of keywords to article by the author is different in their form and perspective. Though they were not choosing the keywords in a controlled vocabulary the keywords were used to describe their own content in the article. Two algorithms were used to arrange the keywords according to topics and the keywords inside the journals will be scored depending on its presence in various fields in the article. Depending on the score the journals will be ranked in such a way that the author can decide whether to open the article for their requirement. This is achieved through Latent Dirichlet Allocation, RankSVM and TF-IDF Algorithms.

Comparative Study on Perceived Trust of Topic Modeling Based on Affective Level of Educational Text

Latent dirichlet allocation (LDA) is a representative topic model to extract keywords related to latent topics embedded in a document set. Despite its effectiveness in finding underlying topics in documents, the traditional algorithm of LDA does not have a process to reflect sentimental meanings in text for topic extraction. Focusing on this issue, this study aims to investigate the usability of both LDA and sentiment analysis (SA) algorithms based on the affective level of text. This study defines the affective level of a given set of paragraphs and attempts to analyze the perceived trust of the methodologies in regards to usability. In our experiments, the text of the college scholastic ability test was selected as the set of evaluation paragraphs, and the affective level of the paragraphs was manipulated into three levels (low, medium, and high) as an independent variable. The LDA algorithm was used to extract the keywords of the paragraph, while SA was used to identify the positive or negative mood of the extracted subject word. In addition, the perceived trust score of the algorithm was evaluated by the subjects, and this study verifies whether there is a difference in the score according to the affective levels of the paragraphs. The results show that paragraphs with low affect lead to the high perceived trust of LDA from the participants. However, the perceived trust of SA does not show a statistically significant difference between the affect levels. The findings from this study indicate that LDA is more effective to find topics in text that mainly contains objective information.

A service recommendation algorithm with the transfer learning based matrix factorization to improve cloud security

Recommendation system (RS) is designed to provide personalized services based on the users’ historical data. It has been applied in various fields and is expected to recommend the suitable services for the different kinds of users. Considering the importance of individual privacy, current users gradually tend not to expose personal information. This means RS may face the highly sparse datasets in the fields of cloud security. In general, the accuracy of recommendation will be improved with the growth of individual data, but the cold start problem is exactly in this contradictory phenomenon: this question evolves to produce sufficiently accurate recommendation result under the data scarcity problem. RS has to recommend services for the rarely historical data users and the latent users might drain along with the production of counter effects. To alleviate data scarcity problem in cloud security environment, this work is to introduce similar domain knowledge based on the transfer learning. Besides, the content and location based methods have been proved that these ideas work under this situation. So, this work also employs latent dirichlet allocation (LDA) to analysis the service descriptions and explore the relationship between the content and location information. In this framework, the suitable combination of LDA and word2vec models will balance the accuracy and speed which benefit service recommendation particularly. The related experiments demonstrate the effectiveness on the real word dataset. It can be found that the transfer learning based word2vec model shows the potentiality to explore the relationship between topic words, and improve the LDA algorithm from the content relationship. This proves that in both cold start environment and warm start environment, the proposed algorithm is more robust than other model-based state-of-art methods.

Review and Implementation of Topic Modeling in Hindi

ABSTRACTDue to the widespread usage of electronic devices and the growing popularity of social media, a lot of text data is being generated at the rate never seen before. It is not possible for humans to read all data generated and find what is being discussed in his field of interest. Topic modeling is a technique to identify the topics present in a large set of text documents. In this paper, we have discussed the widely used techniques and tools for topic modeling. There has been a lot of research on topic modeling in English, but there is not much progress in the resource-scarce languages like Hindi despite Hindi being spoken by millions of people across the world. In this paper, we have discussed the challenges faced in developing topic models for Hindi. We have applied Latent Semantic Indexing (LSI), Non-negative Matrix Factorization (NMF), and Latent Dirichlet Allocation (LDA) algorithms for topic modeling in Hindi. The outcomes of the topic model algorithms are usually difficult to interpret for the common user. We have used various visualization techniques to represent the outcomes of topic modeling in a meaningful way. Then we have used the metrics like perplexity and coherence to evaluate the topic models. The results of Topic modeling in Hindi seem to be promising and comparable to some results reported in the literature on English datasets.

Do tweets create value? A multi-period analysis of Twitter use and content of tweets for manufacturing firms

In this research we enquire if adoption of Twitter by manufacturing firms creates any value for the firm. We conduct two studies to examine the relationship between Twitter related activities of manufacturing firms and the market reaction towards these firms. We collect a novel multi-period dataset and analyse the overall impact of adoption of Twitter on Tobin's Q by employing a propensity score matching and difference-in-difference research design. Our findings suggest that adoption of Twitter increases the value of the firm post adoption. We also conduct additional robustness check such as use of Industry Week data as a proxy of firm value and find our results to be consistent. We adopt a text mining-based approach and examine the communication environment of the manufacturing firms. We use the Latent Dirichlet Allocation (LDA) algorithm for short texts and identify six broad topics among tweets posted by firms. Our panel regression based analysis suggests that there is positive association between divulging product related information and Tobin's Q. Our research showcases the strong impact of use of Twitter and contributes to the nascent literature on firm generated content. It is likely to encourage managers of manufacturing firms to start actively using Twitter for sharing product related information on social media.

Research on Enterprise Hidden Danger Association Rules Based on Text Analysis

Descriptive fields are used in the daily operation of an enterprise as a dimension for recording hidden danger letters. However, it is quite difficult to extract corresponding effective data from such text information to guide the operation of the enterprise. In view of this problem, this paper first grouped the hidden danger data of different enterprise types, then used Chinese word segmentation technology to transform the corresponding descriptive fields into structural data, extracted the topic model using Latent Dirichlet Allocation (LDA) algorithm, and finally used Apriori algorithm to find the association rules of hidden dangers under different enterprise types. After the analysis of the experimental results, the association rules validated accord with common sense and can provide data support for hidden danger supervision.

Deciphering published articles on cyberterrorism: a latent Dirichlet allocation algorithm application

An emerging issue called cyberterrorism is a fatal problem causing a disturbance in the cyberspace. To unravel underlying issues about cyberterrorism, it is imperative to look into available documents found in the NATO's repository. Extraction of articles using web-mining technique and performed topic modelling on NLP. Moreover, this study employed latent Dirichlet allocation algorithm, an unsupervised machine learning to generate latent themes from the text corpus. An identified five underlying themes revealed based on the result. Finally, a profound understanding of cyberterrorism as a pragmatic menace of the cyberspace through a worldwide spread of black propaganda, recruitment, computer and network hacking, economic sabotage and others revealed. As a result, countries around the world, including NATO and its allies, had continuously improved its capabilities against cyberterrorism.

Framework for defining information quality based on data attributes within the digital shadow using LDA

The amount of data, which is created in companies is increasing due to modern communication technologies and decreasing costs for storing data. This leads to an advancement of methods for data analyses as well as to an increasing awareness of benefits resulting from data-based knowledge. In the context of product service systems and product development, there are two major concepts for providing product information. The digital twin collects every information possible, while the digital shadow provides a sufficient and content-related picture of the product. Since these concepts merge data from different sources, comprehension about information quality and its relation to the data quality becomes immanently important. This paper introduces a framework to determine information quality with respect to data-related and system-related attributes. An extensive literature review with focus on “information quality” and “data quality” identifies the important approaches for describing information and data quality. A latent dirichlet allocation (LDA) algorithm is applied on 371 definitions and identify 12 data-related and system-related attributes for information quality. Those attributes are assigned to six dimensions for information quality. So the proposed framework depicts the relationships between data attributes and the influence on information quality.

Deciphering published articles on cyberterrorism: a latent Dirichlet allocation algorithm application

Deciphering published articles on cyberterrorism: a latent Dirichlet allocation algorithm application

Where communities intermingle, diversity grows - The evolution of topics in ecosystem service research.

We analyze how the content of ecosystem service research has evolved since the early 1990s. Conducting a computational bibliometric content analysis we process a corpus of 14,118 peer-reviewed scientific article abstracts on ecosystem services (ES) from Web of Science records. To provide a comprehensive content analysis of ES research literature, we employ a latent Dirichlet allocation algorithm. For three different time periods (1990–2000, 2001–2010, 2011–2016), we derive nine main ES topics arising from content analysis and elaborate on how they are related over time. The results show that natural science-based ES research analyzes oceanic, freshwater, agricultural, forest, and soil ecosystems. Pollination and land cover emerge as traceable standalone topics around 2001. Social science ES literature demonstrates a reflexive and critical lens on the role of ES research and includes critiques of market-oriented perspectives. The area where social and natural science converge most is about land use systems such as agriculture. Overall, we provide evidence of the strong natural science foundation, the highly interdisciplinary nature of ES research, and a shift in social ES research towards integrated assessments and governance approaches. Furthermore, we discuss potential reasons for observable topic developments.

Construction and Recommendation of a Water Affair Knowledge Graph

Water affair data mainly consists of structured data and unstructured data, and the storage methods of data are diverse and heterogeneous. To meet the needs of water affair information integration, a method of constructing a knowledge graph using a combination of water affair structured and unstructured data is proposed. To meet the needs of a water information search, an information recommendation system for constructing a water affair knowledge graph is proposed. In this paper, the edit distance algorithm and latent Dirichlet allocation (LDA) algorithm are used to construct a water affair structured data and unstructured data combination knowledge graph, and this graph is validated based on the semantic distance algorithm. Finally, this paper uses the recall rate, accuracy rate, and F comprehensive results to compare the algorithms. The evaluation results of the edit distance algorithm and the LDA algorithm exceed 90%, which is greater than the comparison algorithm, thus confirming the validity and accuracy of the construction of a water affair knowledge graph. Furthermore, a set of water affair verification sets is used to verify the recommendation method, which proves the effectiveness of the recommended method.

Supporting governance of mobile application developers from mining and analyzing technical questions in stack overflow

There is a need to improve the direct communication between large organizations that maintain mobile platforms (e.g. Apple, Google, and Microsoft) and third-party developers to solve technical questions that emerge during the project and development of developers’ contributions in a Mobile Software Ecosystem (MSECO). In this context, those organizations may not know how to define and evolve strategies to govern their developers towards achieving their organizational goals. Such organizations use an infrastructure to support developers, for example, questions and answers (Q&A) portals such as Stack Overflow. Interactions among developers in these portals feed a Q&A repository that can serve as a mechanism to understand and define strategies to support developers. In this paper, we mined 1,568,377 technical questions from Stack Overflow related to Android, iOS, and Windows Phone platforms. Next, we performed comparisons among those MSECO regarding: (i) developers’ activity intensity, (ii) hot-topics (using Latent Dirichlet allocation algorithm) from all and more commented/viewed questions, (iii) “What” and “How to” questions, (iv) hot-topics from more viewed unanswered questions, and (v) relationship among questions and official developer events. From the results, we identified four key insights: recruiting, educating, and monitoring strategies; barrier reduction; management of technology insertion; and fostering of relationships. The relevance of the four key insights to support developer governance was evaluated by practitioners through a survey. Finally, for each key insight we associated a total of 10 strategies to support developer governance activities. Such strategies were extracted from 65 studies identified through a systematic mapping of the literature.

Microblog topic evolution computing based on LDA algorithm

AbstractResearch on topic evolution of Microblog is an effective way to analyze network public opinions. This paper proposes a method for mining changing of Microblog topics with time, and realizes topic evolution through topic extraction and topic relevance calculation. Firstly, latent Dirichlet allocation (LDA) model is used to automatically extract topics from different time slices; secondly, a similarity calculation algorithm is designed to calculate relevance of topic content through normalization of similarities among characteristic words and co-occurrence relations, to get evolutionary relationship among sub-topics of different time slices; thirdly, using probability distribution of blog article-topic to calculate topic intensity in each time slice, and then gets evolutionary relationship of topic intensity over time. Experiments show that the proposed topic evolution analysis model can effectively detect the evolution of topic content and intensity of real blogs.

Finding a Common Ground in Human and Machine-Based Text Processing

Language makes human communication possible. Apart from everyday applications, language can provide insights into individuals’ thinking and reasoning. Machine-based analyses of text are becoming widespread in business applications, but their utility in learning contexts are a neglected area of research. Therefore, the goal of the present work is to explore machine-assisted approaches to aid in the analysis of students’ written compositions. A method for extracting common topics from written text is applied to 78 student papers on technology and ethics. The primary tool for analysis is the Latent Dirichlet Allocation algorithm. The results suggest that this machine-based topic extraction method is effective and supports a promising prospect for enhancing classroom learning and instruction. The method may also prove beneficial in other applied applications, like those in clinical and counseling practice.
 References
 
 Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research 3, 993-1022.
 Bruner, J. (1990). Acts of meaning. Cambridge, MA: Harvard University Press.
 Chen, K. Y. M., & Wang, Y. (2007). Latent dirichlet allocation. http://acsweb.ucsd.edu/~yuw176/ report/lda.pdf.
 Chung, C. K., & Pennebaker, J. W. (2008). Revealing dimensions of thinking in open-ended self-descriptions: An automated meaning extraction method for natural language. Journal of research in personality, 42(1), 96-132.
 Feldman, S. (1999). NLP meets the Jabberwocky: Natural language processing in information retrieval. Online Magazine, 23, 62-73. Retrieved from: http://www.onlinemag.net/OL1999/ feldmann5.html
 Mishlove, J. (2010). https://www.youtube.com/watch?v=0XTDLq34M18 (Accessed June 12, 2018).
 Ostrowski, D. A. (2015). Using latent dirichlet allocation for topic modelling in twitter. In Semantic Computing (ICSC), 2015 IEEE International Conference (pp. 493-497). IEEE.
 Pennebaker, J. W. (2004). Theories, therapies, and taxpayers: On the complexities of the expressive writing paradigm. Clinical Psychology: Science and Practice, 11(2), 138-142.
 Pennebaker, J.W., Boyd, R.L., Jordan, K., & Blackburn, K. (2015). The development and psychometric properties of LIWC 2015. Austin, TX: University of Texas at Austin.
 Pennebaker, J. W., Chung, C. K., Frazee, J., Lavergne, G. M., & Beaver, D. I. (2014). When small words foretell academic success: The case of college admissions essays. PLoS ONE, 9(12), e115844.
 Pennebaker, J. W., & King, L. A. (1999). Linguistic styles: Language use as an individual difference. Journal of Personality and Social Psychology, 77(6), 1296-1312.
 Recchia, G., Sahlgren, M., Kanerva, P., & Jones, M. N. (2015). Encoding sequential information in semantic space models: Comparing holographic reduced representation and random permutation. Computational intelligence and neuroscience, 2015, 1-18.
 Salzmann, Z. (2004). Language, Culture, and Society: An Introduction to Linguistic Anthropology (3rd ed). Westview Press.
 Schank, R. C., Goldman, N. M., Rieger III, C. J., & Riesbeck, C. (1973). MARGIE: Memory analysis response generation, and inference on English. In IJCAI, 3, 255-261.
 Taraban, R., Marcy, W. M., LaCour Jr., M. S., & Burgess II, R. A. (2017). Developing machine-assisted analysis of engineering students’ ethics course assignments. Proceedings of the American Society of Engineering Education (ASEE) Annual Conference, Columbus, OH. https://www.asee.org/public/conferences/78/papers/19234/view.
 Taraban, R., Marcy, W. M., LaCour, M. S., Pashley, D., & Keim, K. (2018). Do engineering students learn ethics from an ethics course? Proceedings of the American Society of Engineering Education – Gulf Southwest (ASEE-GSW) Annual Conference, Austin, TX. http://www.aseegsw18.com/papers.html.
 Taraban, R., & Marshall, P. H. (2017). Deep learning and competition in psycholinguistic research. East European Journal of Psycholinguistics, 4(2), 67-74.
 Weizenbaum, J. (1966). ELIZA—a computer program for the study of natural language communication between man and machine. Communications of the ACM, 9(1), 36-45.
 Winograd, T. (1972). Understanding natural language. New York: Academic Press.

Similarity Detection Using Latent Semantic Analysis Algorithm

Similarity View is an application for visually comparing and exploring multiple models of text and collection of document. Friendbook finds ways of life of clients from client driven sensor information, measures the closeness of ways of life amongst clients, and prescribes companions to clients if their ways of life have high likeness. Roused by demonstrate a clients day by day life as life records, from their ways of life are separated by utilizing the Latent Dirichlet Allocation Algorithm. Manual techniques can't be utilized for checking research papers, as the doled out commentator may have lacking learning in the exploration disciplines. For different subjective views, causing possible misinterpretations. An urgent need for an effective and feasible approach to check the submitted research papers with support of automated software. A method like text mining method come to solve the problem of automatically checking the research papers semantically. The proposed method to finding the proper similarity of text from the collection of documents by using Latent Dirichlet Allocation (LDA) algorithm and Latent Semantic Analysis (LSA) with synonym algorithm which is used to find synonyms of text index wise by using the English wordnet dictionary, another algorithm is LSA without synonym used to find the similarity of text based on index. LSA with synonym rate of accuracy is greater when the synonym are consider for matching.

Content analysis of e-petitions with topic modeling: How to train and evaluate LDA models?

E-petitions have become a popular vehicle for political activism, but studying them has been difficult because efficient methods for analyzing their content are currently lacking. Researchers have used topic modeling for content analysis, but current practices carry some serious limitations. While modeling may be more efficient than manually reading each petition, it generally relies on unsupervised machine learning and so requires a dependable training and validation process. And so this paper describes a framework to train and validate Latent Dirichlet Allocation (LDA), the simplest and most popular topic modeling algorithm, using e-petition data. With rigorous training and evaluation, 87% of LDA-generated topics made sense to human judges. Topics also aligned well with results from an independent content analysis by the Pew Research Center, and were strongly associated with corresponding social events. Computer-assisted content analysts can benefit from our guidelines to supervise every process of training and evaluation of LDA. Software developers can benefit from learning the demands of social scientists when using LDA for content analysis. These findings have significant implications for developing LDA tools and assuring validity and interpretability of LDA content analysis. In addition, LDA topics can have some advantages over subjects extracted by manual content analysis by reflecting multiple themes expressed in texts, by extracting new themes that are not highlighted by human coders, and by being less prone to human bias.

Spatial-Temporal Event Detection from Geo-Tagged Tweets

As one of the most popular social networking services in the world, Twitter allows users to post messages along with their current geographic locations. Such georeferenced or geo-tagged Twitter datasets can benefit location-based services, targeted advertising and geosocial studies. Our study focused on the detection of small-scale spatial-temporal events and their textual content. First, we used Spatial-Temporal Density-Based Spatial Clustering of Applications with Noise (ST-DBSCAN) to spatially-temporally cluster the tweets. Then, the word frequencies were summarized for each cluster and the potential topics were modeled by the Latent Dirichlet Allocation (LDA) algorithm. Using two years of Twitter data from four college cities in the U.S., we were able to determine the spatial-temporal patterns of two known events, two unknown events and one recurring event, which then were further explored and modeled to identify the semantic content about the events. This paper presents our process and recommendations for both finding event-related tweets as well as understanding the spatial-temporal behaviors and semantic natures of the detected events.