1
September 2012
RecSys '12: Proceedings of the sixth ACM conference on Recommender systems
Publisher: ACM
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 4, Downloads (12 Months): 29, Downloads (Overall): 584
Full text available:
PDF
Social media sites have used recommender systems to suggest items users might like but are not already familiar with. These items are typically movies, books, pictures, or songs. Here we consider an alternative class of items - pictures posted by design-conscious individuals. We do so in the context of a ...
Keywords:
social media, mobile, trend detection
Keywords:
trend detection
Full Text:
... while the other results answer a morefundamental question - whether trend detection helps the recom-mendation process; and the answer is a definite ...
... model the two processes here treatedseparately - collaborative filtering and trend detection. . This couldbe done by, for example, combing Amatriain et ...
2
May 2015
WWW '15: Proceedings of the 24th International Conference on World Wide Web
Publisher: International World Wide Web Conferences Steering Committee
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 3, Downloads (12 Months): 33, Downloads (Overall): 142
Full text available:
PDF
Trending search topics cause unpredictable query load spikes that hurt the end-user search experience, particularly the mobile one, by introducing longer delays. To understand how trending search topics are formed and evolve over time, we analyze 21 million queries submitted during periods where popular events caused search query volume spikes. ...
Keywords:
pockettrend, trend detection, web search
Keywords:
trend detection
References:
N. G. Golbandi, L. K. Katzir, Y. K. Koren, and R. L. Lempel. Expediting Search Trend Detection via Prediction of Query Counts. In Proc. of WSDM, 2013.
M. Mathioudakis and N. Koudas. TwitterMonitor: trend detection over the twitter stream. In Proc. of SIGMOD, pages 1155--1158, 2010.
Full Text:
... to form events.3.1.1 Trending Keyword DetectionAs in related work on trend detection [20, 24, 9], we leveragethe observation that in the absence ... + newsTrend #2cnn+fox+newsTrend#1 and Trend#2 mergeFigure 8: Detailed example of trend detection and trendingkeywords grouping (Boston marathon bombing).together more than 20% of ... threshold could be adjusted depending on thedatacenter?s requirements.To illustrate how trend detection works in practice, Figure 8shows the trend evolution for the ...
... search engines already offer products such as GoogleTrends [6]. Our trend detection approach leverages well-knowntechniques for trend analysis [20, 24], and is ...
... K. Katzir, Y. K. Koren, and R. L. Lempel.Expediting Search Trend Detection via Prediction of QueryCounts. In Proc. of WSDM, 2013.[10] A. ...
3
June 2010
SIGMOD '10: Proceedings of the 2010 ACM SIGMOD International Conference on Management of data
Publisher: ACM
Bibliometrics:
Citation Count: 162
Downloads (6 Weeks): 44, Downloads (12 Months): 460, Downloads (Overall): 4,543
Full text available:
PDF
We present TwitterMonitor, a system that performs trend detection over the Twitter stream. The system identifies emerging topics (i.e. 'trends') on Twitter in real time and provides meaningful analytics that synthesize an accurate description of each topic. Users interact with the system by ordering the identified trends using different criteria ...
Keywords:
trend detection, social media analysis
Title:
TwitterMonitor: trend detection over the twitter stream
Keywords:
trend detection
Abstract:
<p>We present TwitterMonitor, a system that performs trend detection over the Twitter stream. The system identifies emerging topics (i.e. ... own description for each trend.</p> <p>We discuss the motivation for trend detection over social media streams and the challenges that lie therein. ... challenges that lie therein. We then describe our approach to trend detection, , as well as the architecture of TwitterMonitor. Finally, we ...
Full Text:
TwitterMonitor.dviTwitterMonitor: Trend Detection over the Twitter StreamMichael MathioudakisComputer ScienceUniversity of TorontoToronto, Ontario, Canadamathiou@cs.toronto.eduNick ... their own description for each trend.We discuss the motivation for trend detection over so-cial media streams and the challenges that lie therein. ... the challenges that lie therein. Wethen describe our approach to trend detection, , as well asthe architecture of TwitterMonitor. Finally, we lay ... that attract the attention of alarge fraction of Twitter users. Trend detection is thus ofhigh value to news reporters and analysts, as ... 2009,Twitter was immediately flooded with an enormous volumeof related commentary. Trend detection is also importantfor online marketing professionals and opinion tracking com-panies, ... to topics that capture the public?sattention. The requirement for real-time trend detection isonly natural for a live stream where topics of discussion ... ofour knowledge, our system is the first research-oriented efforttowards real-time trend detection over the Twitter stream.We envision our highly scalable approach to ... follows, we describe how TwitterMonitor tack-les the challenge of real-time trend detection, , as well as itsarchitecture. We conclude with a description ... itsarchitecture. We conclude with a description of our demon-stration scenario.2. TREND DETECTION AND ANALYSISTwitterMonitor performs trend detection in two steps andanalyzes trends in a third step. First, ...
... importantNBA match taking place.TwitterMonitor treats bursty keywords as ?entry points?for trend detection. . In other words, whenever a keywordexhibits bursty behavior, TwitterMonitor ...
4
June 2014
WebSci '14: Proceedings of the 2014 ACM conference on Web science
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 6, Downloads (12 Months): 53, Downloads (Overall): 185
Full text available:
PDF
Monitoring rates of alcohol consumption across the UK is a timely problem due to ever-increasing drinking levels. This has led to calls from public services (e.g. police and health services) to assess the effect it is having on people and society. Current research methods that are utilised to assess consumption ...
Keywords:
trend detection, twitter, alcohol, keyword analysis, sns
Keywords:
trend detection
References:
M. Mathioudakis and N. Koudas. Twittermonitor: trend detection over the twitter stream. pages 1155--1158, 2010.
5
February 2013
WSDM '13: Proceedings of the sixth ACM international conference on Web search and data mining
Publisher: ACM
Bibliometrics:
Citation Count: 12
Downloads (6 Weeks): 5, Downloads (12 Months): 20, Downloads (Overall): 330
Full text available:
PDF
The massive volume of queries submitted to major Web search engines reflects human interest at a global scale. While the popularity of many search queries is stable over time or fluctuates with periodic regularity, some queries experience a sudden and ephemeral rise in popularity that is unexplained by their past ...
Keywords:
query count prediction, search trend detection
Title:
Expediting search trend detection via prediction of query counts
Keywords:
search trend detection
Abstract:
... defines precision, recall and latency metrics related to top-k search trend detection. . Then, observing that many trend detection algorithms rely on query counts, we develop a linear auto-regression ... counts. Subsequently, we tap the predicted counts to expedite search trend detection by plugging them into an existing trend detection scheme.</p> <p>Experimenting with query logs from a major Web search ... on the emitted trends. We show an average reduction in trend detection latency of roughly twenty minutes, with a negligible impact on ...
References:
M. Mathioudakis and N. Koudas. Twittermonitor: trend detection over the twitter stream. In SIGMOD Conference, pages 1155--1158, 2010.
Full Text:
latency-editorial-over-w.epsExpediting Search Trend Detection via Prediction of QueryCountsNadav GolbandiYahoo! Labs, Haifa, Israelnadavg@yahoo-inc.comLiran Katzir?Microsoft Research,Advanced ... formally de?nes precision, recall and latencymetrics related to top-k search trend detection. . Then, ob-serving that many trend detection algorithms rely on querycounts, we develop a linear auto-regression model ... query counts. Subsequently, we tap the predictedcounts to expedite search trend detection by plugging theminto an existing trend detection scheme.Experimenting with query logs from a major Web searchengine, we ... on the emitted trends. We show an average re-duction in trend detection latency of roughly twenty min-utes, with a negligible impact on ... 978-1-4503-1869-3/13/02 ...$15.00.Categories and Subject DescriptorsH.3.3 [Information Search and Retrieval]: Information?lteringKeywordsSearch trend detection, , query count prediction1. INTRODUCTIONMajor Web search engines continuously receive ...
... level, we plug the predicted future query countsinto an existing trend detection algorithm that relies on ac-cess to query counts. With an ... to query counts. With an ideal (oracle) predictor, thiswould expedite trend detection by pre-producing future re-sults earlier.Concretely, we incorporated our predicted query ... re-sults earlier.Concretely, we incorporated our predicted query countsinto the search trend detection algorithm of Dong et al. [9].We report both the stand-alone ... outputs).Al-Bawab et al. [1] extended [9] to provide a location-aware296search trends detection algorithm using geographical prop-erties associated with query log entries.Chen et ... mod-els [18]. Mathioudakis et al [19] provide a framework foronline trends detection in Twitter.While all these prior works o?er new signal sources, ...
... predicted counts are then fed as input intothe baseline search trends detection algorithm, Algorithm 1.The baseline algorithm then emits trends based on ...
... the recall, precision and latencymetrics by which we judge search trend detection algorithms.We assume that algorithms emit top-k trends every timeunit, and ... Aswe are mostly concerned with the comparison of two com-peting trend detection algorithms A and B, we will denoteby At, Bt and ... causing what are essentially di?erent search trends.Moving on to de?ne trend detection latency, here we wishto measure the amount by which one ...
... de?ning latency, precision and recall metrics for the eval-uation of trend detection algorithms.7. REFERENCES[1] Z. Al-Bawab, G. H. Mills, and J.-F. Crespo. ...
6
August 2014
KDD '14: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining
Publisher: ACM
Bibliometrics:
Citation Count: 11
Downloads (6 Weeks): 22, Downloads (12 Months): 155, Downloads (Overall): 900
Full text available:
PDF
Social media such as Twitter or weblogs are a popular source for live textual data. Much of this popularity is due to the fast rate at which this data arrives, and there are a number of global events - such as the Arab Spring - where Twitter is reported to ...
Keywords:
text-mining, outlier detection, trend detection, hashing
Keywords:
trend detection
References:
M. Mathioudakis and N. Koudas. Twittermonitor: trend detection over the Twitter stream. In Proc. SIGMOD, pages 1155--1158, 2010.
Full Text:
... following subsections, we will discuss some impor-tant aspects for emerging trend detection. . First of all, wediscuss how to measure significance of ...
... single strongtrend may mask other trends in the data set.3.3 Trend Detection on CooccurrencesEquation 3 and Equation 4 can be applied to ... noisy and exhibit a toohigh variance to be useful for trend detection. . A simple butreliable approach estimating x is to use ...
... 225 bytes of memory(32 Megabytes).4.5 Online DemonstrationThe results of our trend detection system are available athttp://signi-trend.appspot.com/ for exploration.5. CONCLUSIONSIn this article, we ...
7
November 2013
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03
Publisher: IEEE Computer Society
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 3, Downloads (12 Months): 13, Downloads (Overall): 28
Full text available:
PDF
Information about upcoming trends is a valuable knowledge for both, companies and individuals. Detecting trends for a certain topic is of special interest. According to the latest information over 200 million blogs exist in the World Wide Web. Hence, every day millions of posts are published. These blogs contain an ...
Keywords:
Social Media, Trend Detection, Blog, Web Mining
Keywords:
Social Media, Trend Detection, Blog, Web Mining
References:
A. Kontostathis, L. Galitsky, W. M. Pottenger, S. Roy, and D. J. Phelps, "A survey of emerging trend detection in textual data mining," 2003.
A. Kontostathis, L. M. Galitsky, W. M. Pottenger, S. Roy, and D. J. Phelps, "A Survey of Emerging Trend Detection in Textual Data Mining," Language, pp. 1-44, 2003.
Full Text:
... detect reliable trends automatically.This paper presents an approach that combines trend- -detection for structured and unstructured data. As a result,this approach ?ts ... presented in detail in Section IV.In Section V the presented trend- -detection algorithm getsevaluated to provide a deeper understanding of how thisdetection ... WORKIn their article Kontostathis et al. [3] described differentkinds of trend- -detection systems. They divided the trend- -detection systems into two main categories. The semi- au-tomatic systems, which ... Thesecond group is the group of fully-automatic trend-detectionsystems. The fully-automatic trend- -detection approaches pro-duce output without interaction with the user.A trend- -detection system consists of different componentssuch as linguistic and statistical features, ... results to the user in a user-friendly visualization.A very sophisticated trend- -detection model was introducedby Abe et al. [4]. Their system ?nds ...
... titles for two selected conferences.Currently, there a few approaches for trend- -detection insidethe World Wide Web with more or less good results. ... andunstructured data of the blogosphere in order to detect trends.III. TREND- -DETECTION PREREQUISITESTo detect trends inside the blogosphere many differentsteps have to ... trends later on.A. Time WindowDue to the fact that the trend- -detection should work withuser input and detect the latest trends,a certain ... negative. These meanings areexplained in more detail in Section IV-D3.IV. TREND- -DETECTION ALGORITHMThe different aspects monitored over time are described inmore detail. ...
... 2. Blog Posts Meanings term termterm7.Fig. 1. Overview of the trend- -detection algorithm42A. Link AnalysisOne of the most powerful structures inside the ... different text sourcesinside the blogosphere. Furthermore, the quality of the trend- -detection results can be improved by including additionalmeta-information. The best known ...
... slope are shown in Table I.V. EVALUATIONThis Section evaluates the trend- -detection algorithm itselfin more detail. We want to take a deeper ... is made to make an assumptionas to how reliable the trend- -detection system is using anexperiment. Therefore the speci?ed time window is ...
... is just a verylimited experiment. Nevertheless, it shows that the trend- -detection could probably be used for prediction of trends.Therefore, further evaluation ... understanding of the trends and would deliver morevaluable information.VII. CONCLUSIONFor trend- -detection based on the blogosphere three differentaspects are taken into account ... Pottenger, S. Roy, and D. J. Phelps,?A survey of emerging trend detection in textual data mining,? 2003.[2] J. B. C. M. Patrick ... Pottenger, S. Roy, and D. J.Phelps, ?A Survey of Emerging Trend Detection in Textual Data Mining,?Language, pp. 1?44, 2003.[4] H. Abe and ...
8
November 2012
WIDM '12: Proceedings of the twelfth international workshop on Web information and data management
Publisher: ACM
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 3, Downloads (12 Months): 22, Downloads (Overall): 265
Full text available:
PDF
The Social Web makes visible the ebb and flow of popular interest in topics both newsworthy ("GulfSpill") and trivial ("Lolcat"). Understanding this emergent behavior is a fundamental goal for Social Web research. Key problems include discovering emergent topics from online text sources, modeling burst activity, and predicting the future trajectory ...
Keywords:
change point analysis, social web, trend detection, collaborative tagging
Keywords:
trend detection
Full Text:
... Design Methodology; H.2.8[Information Systems]: Database Application?Data Min-ingKeywordssocial web, collaborative tagging, trend detection, , changepoint analysis1. INTRODUCTIONUser-generated content on the Social Web comes ...
9
June 2017
TVX '17: Proceedings of the 2017 ACM International Conference on Interactive Experiences for TV and Online Video
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 46, Downloads (12 Months): 46, Downloads (Overall): 46
Full text available:
PDF
Context-awareness has become a critical factor in improving the predictions of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches such as tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction dataset from a WebTV platform, ...
Keywords:
context-aware applications, user experience, video on demand, privacy reserving recommender, trend detection
Keywords:
trend detection
References:
S. Hendrickson, J. Kolb, B. Lehman, and J. Montague. Trend detection in social data. Technical report, Twitter, 2015.
Full Text:
... Twitter social media text streams; and 2) we showthat the trends detected in the Twitter social stream highlycover peaks observed in the ...
... on ?t is also provided. Contrary to the usual casewhere trend detection is favored to be as early as possible, inour setup, ...
10
November 2013
CCS '13: Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Publisher: ACM
Bibliometrics:
Citation Count: 10
Downloads (6 Weeks): 1, Downloads (12 Months): 53, Downloads (Overall): 513
Full text available:
PDF
Identifying malicious web sites has become a major challenge in today's Internet. Previous work focused on detecting if a web site is malicious by dynamically executing JavaScript in instrumented environments or by rendering web sites in client honeypots. Both techniques bear a significant evaluation overhead, since the analysis can take ...
Keywords:
malware detection, clustering, infection vector identification, web-based malware, infection campaigns, trend detection, computer security, web dynamics
Keywords:
trend detection
Full Text:
... processKeywordscomputer security; web-based malware; malware detection;infection vector identification; infection campaigns; clustering;trend detection; ; web dynamicsPermission to make digital or hard copies of ...
... a snapshot. Consequently, it might then bepossible to evade the trend detection step in the first place.Additionally, we might also miss infection ... which,in turn, allows us to leverage more computationally-expensivefeatures to increase trend detection accuracy.Lastly, while the trend detection step is purely static, todetect malicious behavior, the ?-system relies ...
11
July 2010
KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining
Publisher: ACM
Bibliometrics:
Citation Count: 12
Downloads (6 Weeks): 5, Downloads (12 Months): 55, Downloads (Overall): 1,353
Full text available:
PDF
We describe a system that monitors social and mainstream media to determine shifts in what people are thinking about a product or company. We process over 100,000 news articles, blog posts, review sites, and tweets a day for mentions of items (e.g., products) of interest, extract phrases that are mentioned ...
Keywords:
competitive intelligence, sentiment detection, trend detection, reputation management, brand management, communication, entity extraction, social media, text mining, buzz
Keywords:
trend detection
References:
A. Kontostathis, L. Galitsky, W. M. Pottenger, S. Roy, and D. J. Phelps. A survey of emerging trend detection in textual data mining. in Survey of Text Mining, pp 185--224. 2003
Full Text:
... Text Analytics General Terms Algorithms Keywords Text Mining, Sentiment Detection, Trend Detection, , Entity Extraction, Brand Management, Buzz, Communication, Competitive Intelligence, Reputation ...
... name of ?Topic Detection and Tracking? (TDT) [1] or 62?Emerging Trend Detection? ? [8] where news articles are clustered into groups about ...
... S. Roy, and D. J. Phelps. A survey of emerging trend detection in textual data mining. in Survey of Text Mining, pp ...
12
October 2014
PCI '14: Proceedings of the 18th Panhellenic Conference on Informatics
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 7, Downloads (12 Months): 20, Downloads (Overall): 30
Full text available:
PDF
The rapidly growing wealth of published scientific work, produced by researchers and scholars, has resulted in a pressing need for more effective processes towards reviewing scientific articles and research data, organizing data journals, as well as for improved tools and techniques for bibliographic analysis and management of scientometrics. The ongoing ...
Keywords:
data sources, evaluation metrics, peer review, pilot-driven, web interface, adaptor, data journals, platform architecture, scientific collaboration, social networks, trends analysis, Open data, biomedicine, datasets, integration, scientific information, trends detection, open access, scientometrics, semantic web, service oriented architecture
Keywords:
trends detection
Full Text:
... social networks, semantic web, biomedicine, data journals, datasets, peer review, trends detection, , trends analysis, scientific collaboration, evaluation metrics, scientometrics, platform architecture, ...
... post-review discussions. iii. Data mining for biomedical and clinical research trends detection and analysis. This pilot emphasizes the ability of the OpenScienceLink ...
13
July 2016
SSDBM '16: Proceedings of the 28th International Conference on Scientific and Statistical Database Management
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 6, Downloads (12 Months): 53, Downloads (Overall): 53
Full text available:
PDF
The analysis of social media data poses several challenges: first of all, the data sets are very large, secondly they change constantly, and third they are heterogeneous, consisting of text, images, geographic locations and social connections. In this article, we focus on detecting events consisting of text and location information, ...
Keywords:
geo-social media, time-series analysis, online control charts, rich geo-spatial data, Local event detection, anomaly detection, bursty topic detection, change detection, scalable real-time data analysis, streaming algorithm, trend detection
Keywords:
trend detection
References:
M. Mathioudakis and N. Koudas. "Twittermonitor: trend detection over the Twitter stream". In: Proceedings of the ACM International Conference on Management of Data (SIGMOD), Indianapolis, IN. 2010, pp. 1155--1158.