scholarly journals Priolog: Mining Important Logs via Temporal Analysis and Prioritization

2019 ◽  
Vol 11 (22) ◽  
pp. 6306
Author(s):  
Byungchul Tak ◽  
Seorin Park ◽  
Prabhakar Kudva
Keyword(s):  
Frequency Analysis ◽  
Temporal Analysis ◽  
It Services ◽  
Critical Part ◽  
Software Complexity ◽  
Novel Technique ◽  
Problem Diagnosis ◽  
Operational Management ◽  
Small Set ◽  
Ranked List

Log analytics are a critical part of the operational management in today’s IT services. However, the growing software complexity and volume of logs make it increasingly challenging to mine useful insights from logs for problem diagnosis. In this paper, we propose a novel technique, Priolog, that can narrow down the volume of logs into a small set of important and most relevant logs. Priolog uses a combination of log template temporal analysis, log template frequency analysis, and word frequency analysis, which complement each other to generate an accurately ranked list of important logs. We have implemented this technique and applied to the problem diagnosis task of the popular OpenStack platform. Our evaluation indicates that Priolog can effectively find the important logs that hold direct hints to the failure cause in several scenarios. We demonstrate the concepts, design, and evaluation results using actual logs.

scholarly journals Explore changes in the aspects fundamental to the competitiveness of South Africa as a preferred tourist destination

2017 ◽  
Vol 20 (1) ◽  
Author(s):  
Engelina Du Plessis ◽  
Melville Saayman ◽  
Annari Van der Merwe
Keyword(s):  
South Africa ◽  
Frequency Analysis ◽  
Temporal Analysis ◽  
Value For Money ◽  
Tourist Destination ◽  
The Past ◽  
Role Players ◽  
The Relationship ◽  
Shed Light

Background: Tourism is an evolving and changing industry, and keeping up with these changes requires an understanding of the forces and changes that shape this industry’s outcomes. Tourism managers struggle daily to stay ahead in the competition to attract more tourists to destinations. Understanding the strengths and weaknesses of the past could shed light on the advantages of the future.Aim: The aim of this study was to do a temporal analysis of the competitiveness of South Africa as a tourism destination.Setting: This research investigated the competitive position of South Africa as a tourism destination just after the 1994 elections and compared those results to the results of a similar study in 2014.Methods: In this article, a frequency analysis revealed South Africa’s strengths and weaknesses, after which t-tests indicated the relationship between the strengths and weaknesses of the destination and the factors that contribute to South Africa’s competitiveness.Results: South Africa’s strengths include the quality of the food and experience, scenery, variety of accommodation climate and geographical features. It is clear that respondents identified different attributes that contributed to the strengths of the destination in comparison with 2002, where the strengths were wildlife, scenery, cultural diversity, climate, value for money, variety of attractions and specific icons.Conclusion: This research is valuable for South Africa because it informs tourism role players about what respondents perceive to be South Africa’s strengths. Role players can then form strategies that incorporate the strengths to create competitive advantage. This article also indicates the areas in which the country has grown in the past decade as well as indicating which weaknesses remain a problem.

A corpus-based bootstrapping algorithm for Semi-Automated semantic lexicon construction

1999 ◽  
Vol 5 (2) ◽  
pp. 147-156 ◽  
Author(s):  
ELLEN RILOFF ◽  
JESSICA SHEPHERD
Keyword(s):  
Semantic Information ◽  
Word List ◽  
Lexical Information ◽  
Semantic Class ◽  
New Words ◽  
Domain Specific ◽  
Semantic Classes ◽  
Semantic Lexicons ◽  
Small Set ◽  
Ranked List

Many applications need a lexicon that represents semantic information but acquiring lexical information is time consuming. We present a corpus-based bootstrapping algorithm that assists users in creating domain-specific semantic lexicons quickly. Our algorithm uses a representative text corpus for the domain and a small set of ‘seed words’ that belong to a semantic class of interest. The algorithm hypothesizes new words that are also likely to belong to the semantic class because they occur in the same contexts as the seed words. The best hypotheses are added to the seed word list dynamically, and the process iterates in a bootstrapping fashion. When the bootstrapping process halts, a ranked list of hypothesized category words is presented to a user for review. We used this algorithm to generate a semantic lexicon for eleven semantic classes associated with the MUC-4 terrorism domain.

Subjectivity detection in spoken and written conversations

2010 ◽  
Vol 17 (3) ◽  
pp. 397-418 ◽  
Author(s):  
GABRIEL MURRAY ◽  
GIUSEPPE CARENINI
Keyword(s):  
State Of The Art ◽  
Large Set ◽  
Noisy Speech ◽  
Domain Specific ◽  
Novel Technique ◽  
Prosodic Cues ◽  
Alternative Approach ◽  
Small Set ◽  
N Gram ◽  
Speech Recognizer

AbstractIn this work we investigate four subjectivity and polarity tasks on spoken and written conversations. We implement and compare several pattern-based subjectivity detection approaches, including a novel technique wherein subjective patterns are learned from both labeled and unlabeled data, using n-gram word sequences with varying levels of lexical instantiation. We compare the use of these learned patterns with an alternative approach of using a very large set of raw pattern features. We also investigate how these pattern-based approaches can be supplemented and improved with features relating to conversation structure. Experimenting with meeting speech and email threads, we find that our novel systems incorporating varying instantiation patterns and conversation features outperform state-of-the-art systems despite having no recourse to domain-specific features such as prosodic cues and email headers. In some cases, such as when working with noisy speech recognizer output, a small set of well-motivated conversation features performs as well as a very large set of raw patterns.

scholarly journals The Use of Time-Scale Analysis in Forensic Acoustical Investigations

2020 ◽  
Vol 7 ◽  
pp. 6-11
Author(s):  
Luigi Maxmilian Caligiuri ◽  
Domenica Giordano
Keyword(s):  
Frequency Analysis ◽  
Multiresolution Analysis ◽  
Scale Analysis ◽  
Time Frequency ◽  
Novel Technique ◽  
Use Of Time ◽  
Extraneous Noise ◽  
Analysis Technique ◽  
Identification And Characterization

The identification and characterization of noise events is one of the most important task in acousticalforensic analysis. In this field it is often fundamental to distinguish, within a complex acoustical framework, thedifferent noise events, especially because, in many cases, the operator cannot be present at the measurements. Itis fundamental to be able to distinguish the atypical or extraneous noise events from the specific ones underinvestigation and know what type of sources make up the noise climate. To this aim is essential to develop a time- frequency analysis technique able to overcame the known limitations of the “traditional” 1/3 of octave frequencyanalyses. In this paper a novel technique, based on multiresolution analysis, has been developed and applied tosome forensic “typical” problems, showing that a suitable choice of the analysis parameters can be able to answerto the main questions of this field

scholarly journals DL4papers: a deep learning approach for the automatic interpretation of scientific articles

2020 ◽  
Vol 36 (11) ◽  
pp. 3499-3506
Author(s):  
L A Bugnon ◽  
C Yones ◽  
J Raad ◽  
M Gerard ◽  
M Rubiolo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Precision Medicine ◽  
Supplementary Information ◽  
New Approach ◽  
Novel Treatments ◽  
Automatic Interpretation ◽  
Manual Curation ◽  
Small Set ◽  
Key Terms ◽  
Ranked List

Abstract Motivation In precision medicine, next-generation sequencing and novel preclinical reports have led to an increasingly large amount of results, published in the scientific literature. However, identifying novel treatments or predicting a drug response in, for example, cancer patients, from the huge amount of papers available remains a laborious and challenging work. This task can be considered a text mining problem that requires reading a lot of academic documents for identifying a small set of papers describing specific relations between key terms. Due to the infeasibility of the manual curation of these relations, computational methods that can automatically identify them from the available literature are urgently needed. Results We present DL4papers, a new method based on deep learning that is capable of analyzing and interpreting papers in order to automatically extract relevant relations between specific keywords. DL4papers receives as input a query with the desired keywords, and it returns a ranked list of papers that contain meaningful associations between the keywords. The comparison against related methods showed that our proposal outperformed them in a cancer corpus. The reliability of the DL4papers output list was also measured, revealing that 100% of the first two documents retrieved for a particular search have relevant relations, in average. This shows that our model can guarantee that in the top-2 papers of the ranked list, the relation can be effectively found. Furthermore, the model is capable of highlighting, within each document, the specific fragments that have the associations of the input keywords. This can be very useful in order to pay attention only to the highlighted text, instead of reading the full paper. We believe that our proposal could be used as an accurate tool for rapidly identifying relationships between genes and their mutations, drug responses and treatments in the context of a certain disease. This new approach can certainly be a very useful and valuable resource for the advancement of the precision medicine field. Availability and implementation A web-demo is available at: http://sinc.unl.edu.ar/web-demo/dl4papers/. Full source code and data are available at: https://sourceforge.net/projects/sourcesinc/files/dl4papers/. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Twitter Usage Using Common Reference to Tinnitus

2020 ◽  
Vol 29 (2) ◽  
pp. 206-217
Author(s):  
Jianyuan Ni ◽  
Monica L. Bellon-Harn ◽  
Jiang Zhang ◽  
Yueqing Li ◽  
Vinaya Manchaiah
Keyword(s):  
Nonprofit Organizations ◽  
Temporal Trends ◽  
Temporal Analysis ◽  
Cross Sectional ◽  
For Profit ◽  
Common Reference ◽  
Personal Experiences ◽  
Twitter Users ◽  
Sectional Analysis ◽  
Share Information

Objective The objective of the study was to examine specific patterns of Twitter usage using common reference to tinnitus. Method The study used cross-sectional analysis of data generated from Twitter data. Twitter content, language, reach, users, accounts, temporal trends, and social networks were examined. Results Around 70,000 tweets were identified and analyzed from May to October 2018. Of the 100 most active Twitter accounts, organizations owned 52%, individuals owned 44%, and 4% of the accounts were unknown. Commercial/for-profit and nonprofit organizations were the most common organization account owners (i.e., 26% and 16%, respectively). Seven unique tweets were identified with a reach of over 400 Twitter users. The greatest reach exceeded 2,000 users. Temporal analysis identified retweet outliers (> 200 retweets per hour) that corresponded to a widely publicized event involving the response of a Twitter user to another user's joke. Content analysis indicated that Twitter is a platform that primarily functions to advocate, share personal experiences, or share information about management of tinnitus rather than to provide social support and build relationships. Conclusions Twitter accounts owned by organizations outnumbered individual accounts, and commercial/for-profit user accounts were the most frequently active organization account type. Analyses of social media use can be helpful in discovering issues of interest to the tinnitus community as well as determining which users and organizations are dominating social network conversations.

Sign in / Sign up

Export Citation Format

Share Document