Databases and Information Systems Commons^™

A Survey Of Recommender Systems In Twitter, Su Mon Kywe, Ee Peng Lim, Feida Zhu

Research Collection School Of Computing and Information Systems

Twitter is a social information network where short messages or tweets are shared among a large number of users through a very simple messaging mechanism. With a population of more than 100M users generating more than 300M tweets each day, Twitter users can be easily overwhelmed by the massive amount of information available and the huge number of people they can interact with. To overcome the above information overload problem, recommender systems can be introduced to help users make the appropriate selection. Researchers have began to study recommendation problems in Twitter but their works usually address individual recommendation tasks. There …

On Recommending Hashtags In Twitter Networks, Su Mon Kywe, Tuan-Anh Hoang, Ee Peng Lim, Feida Zhu

Research Collection School Of Computing and Information Systems

Twitter network is currently overwhelmed by massive amount of tweets generated by its users. To effectively organize and search tweets, users have to depend on appropriate hashtags inserted into tweets. We begin our research on hashtags by first analyzing a Twitter dataset generated by more than 150,000 Singapore users over a three-month period. Among several interesting findings about hashtag usage by this user community, we have found a consistent and significant use of new hashtags on a daily basis. This suggests that most hashtags have very short life span. We further propose a novel hashtag recommendation method based on collaborative …

Extracting And Normalizing Entity-Actions From Users' Comments, Swapna Gottipati, Jing Jiang

Research Collection School Of Computing and Information Systems

With the growing popularity of opinion-rich resources on the Web, new opportunities and challenges arise and aid people in actively using such information to understand the opinions of others. Opinion mining process currently focuses on extracting the sentiments of the users on products, social, political and economical issues. In many instances, users not only express their sentiments but also contribute their ideas, requests and suggestions through comments. Such comments are useful for domain experts and are referred to as actionable content. Extracting actionable knowledge from online social media has attracted a growing interest from both academia and the industry. We …

Demonstration: Dynamic Sensor Registration And Semantic Processing For Ad-Hoc Mobile Environments (Semmob), Pramod Anantharam, Gary Alan Smith, Josh Pschorr, Krishnaprasad Thirunarayan, Amit P. Sheth

Kno.e.sis Publications

SemMOB enables dynamic registration of sensors via mobile devices, search, and near real-time inference over sensor observations in ad-hoc mobile environments (e.g., fire fighting). We demonstrate SemMOB in the context of an emergency response use case that requires automatic and dynamic registrations of sensor devices and annotation of sensor observations, decoding of latitude-longitude information in terms of human sensible names, fusion and abstraction of sensor values using background knowledge, and their visualization using mash-up.

Using Social Influence To Predict Subscriber Churn, Derek Doran, Veena Mendiratta, Chitra Phadke, Dan Kushnir, Huseyin Uzunalioglu

Kno.e.sis Publications

The saturation of mobile phone markets has resulted in rising costs for operators to obtain new customers. These operators thus focus their energies on identifying users that will churn so they can be targeted for retention campaigns. Typical churn prediction algorithms identify churners based on service usage metrics, network performance indicators, and demographic information. Social and peer-influence to churn, however, is usually not considered. In this paper, we describe a new churn prediction algorithm that incorporates the influence churners spread to their social peers. Using data from a major service provider, we show that social influence improves churn prediction and …

Understanding User Triads On Facebook, Derek Doran, Alberta De La Rosa Algarin, Swapna S. Gokhale

Kno.e.sis Publications

Contemporary approaches that analyze user behavior on online social networks only consider interactions among dyads, which are pairs of directly connected users. A large body of sociological work, however, suggests that mutual connections among users can influence their activities, leading to differences between two- and three-way interactions. This paper explores the dynamics of triads among Facebook users based on the wall posts from the New Orleans regional network. Initially, each connection is categorized as a close friendship or an acquiantance, contingent on the number of wall posts exchanged. Subsequently, the impact of different types of connections comprising triads is examined …

How I Would Like Semantic Web To Be, For My Children., Raghava Mutharaju

Kno.e.sis Publications

Semantic Web, since its inception, has gone through lot of developments in its relatively nascent existence; right from people's perception, to the standards and to its adoption by the industry and more importantly by the scientific community. This impressive growth only seems to increase. In this paper, we project this growth to the next 10 years and highlight some of the facets on which Semantic Web could have a major impact on. We also present the challenges that Semantic Web and its community has to deal with in order to get there.

An Efficient Bit Vector Approach To Semantics-Based Machine Perception In Resource-Constrained Devices, Cory Andrew Henson, Krishnaprasad Thirunarayan, Amit P. Sheth

Kno.e.sis Publications

The primary challenge of machine perception is to define efficient computational methods to derive high-level knowledge from low-level sensor observation data. Emerging solutions are using ontologies for expressive representation of concepts in the domain of sensing and perception, which enable advanced integration and interpretation of heterogeneous sensor data. The computational complexity of OWL, however, seriously limits its applicability and use within resource-constrained environments, such as mobile devices. To overcome this issue, we employ OWL to formally define the inference tasks needed for machine perception – explanation and discrimination – and then provide efficient algorithms for these tasks, using bit-vector encodings …

Iexplore: Interactive Browsing And Exploring Biomedical Knowledge, Vinh Nguyen, Olivier Bodenreider, Jagannathan Srinivasan, Todd Minning, Thomas Rindflesch, Bastien Rance, Ramakanth Kavuluru, Himi Yalamanchili, Krishnaprasad Thirunarayan, Satya S. Sahoo, Amit P. Sheth

Kno.e.sis Publications

We present iExplore, a Semantic Web based application that helps biomedical researchers study and explore biomedical knowledge interactively. iExplore uses the Biomedical Knowledge Repository (BKR), which integrates knowledge from various sources ranging from information extracted from biomedical literature (from PubMed) to many structured vocabularies in the Unified Medical Language System (UMLS). The current version of BKR provides a unified provenance representation for 12 million semantic predications (triples with a predicate connecting a subject and an object) derived from 87 vocabulary families in the UMLS and 14 million predications extracted from 21 million PubMed abstracts. To engage the domain experts in …

Computing Perception From Sensor Data, Payam Barnaghi, Frieder Ganz, Cory Andrew Henson, Amit P. Sheth

Kno.e.sis Publications

This paper describes a framework for perception creation from sensor data. We propose using data abstraction techniques, in particular Symbolic Aggregate Approximation (SAX), to analyse and create patterns from sensor data. The created patterns are then linked to semantic descriptions that define thematic, spatial and temporal features, providing highly granular abstract representation of the raw sensor data. This helps to reduce the size of the data that needs to be communicated from the sensor nodes to the gateways or highlevel processing components. We then discuss a method that uses abstract patterns created by SAX method and occurrences of different observations …

Privacy Preserving Boosting In The Cloud With Secure Half-Space Queries, Shumin Guo, Keke Chen

Kno.e.sis Publications

This paper presents a preliminary study on the PerturBoost approach that aims to provide efficient and secure classifier learning in the cloud with both data and model privacy preserved.

A Probabilistic Graphical Model For Topic And Preference Discovery On Social Media, Lu Liu, Feida Zhu, Lei Zhang, Shiqiang Yang

Research Collection School Of Computing and Information Systems

Many web applications today thrive on offering services for large-scale multimedia data, e.g., Flickr for photos and YouTube for videos. However, these data, while rich in content, are usually sparse in textual descriptive information. For example, a video clip is often associated with only a few tags. Moreover, the textual descriptions are often overly specific to the video content. Such characteristics make it very challenging to discover topics at a satisfactory granularity on this kind of data. In this paper, we propose a generative probabilistic model named Preference-Topic Model (PTM) to introduce the dimension of user preferences to enhance the …

Influentials, Novelty, And Social Contagion: The Viral Power Of Average Friends, Close Communities, And Old News, Nicholas Harrigan, Palakorn Achananuparp, Ee Peng Lim

Research Collection School Of Computing and Information Systems

What is the effect of (1) popular individuals, and (2) community structures on the retransmission of socially contagious behavior? We examine a community of Twitter users over a five month period, operationalizing social contagion as ‘retweeting’, and social structure as the count of subgraphs (small patterns of ties and nodes) between users in the follower/following network. We find that popular individuals act as ‘inefficient hubs’ for social contagion: they have limited attention, are overloaded with inputs, and therefore display limited responsiveness to viral messages. We argue this contradicts the ‘law of the few’ and ‘influentials hypothesis’. We find that community …

Talk Versus Work: Characteristics Of Developer Collaboration On The Jazz Platform, Subhajit Datta, Renuka Sindhgatta, Bikram Sengupta

Research Collection School Of Computing and Information Systems

IBM's Jazz initiative offers a state-of-the-art collaborative development environment (CDE) facilitating developer interactions around interdependent units of work. In this paper, we analyze development data across two versions of a major IBM product developed on the Jazz platform, covering in total 19 months of development activity, including 17,000+ work items and 61,000+ comments made by more than 190 developers in 35 locations. By examining the relation between developer talk and work, we find evidence that developers maintain a reasonably high level of connectivity with peer developers with whom they share work dependencies, but the span of a developer's communication goes …

Recent Advances In Integrating Owl And Rules, Matthias Knorr, David Carral Martinez, Pascal Hitzler, Adila A. Krisnadhi, Frederick Maier, Cong Wang

Computer Science and Engineering Faculty Publications

As part of the quest for a unifying logic for the Semantic Web Technology Stack, a central issue is finding suitable ways of integrating description logics based on the Web Ontology Language (OWL) with rule-based approaches based on logic programming. Such integration is difficult since naive approaches typically result in the violation of one or more desirable design principles. For example, while both OWL 2 DL and RIF Core (a dialect of the Rule Interchange Format RIF) are decidable, their naive union is not, unless carefully chosen syntactic restrictions are applied.

We report on recent advances and ongoing work by …

A Tableau Algorithm For Description Logics With Nominal Schema, Adila Krisnadhi, Pascal Hitzler

Computer Science and Engineering Faculty Publications

We present a tableau algorithm for the description logic ALCOV. This description logic is obtained by extending the description logic ALCO with the expressive nominal schema construct that enables DL-safe datalog with predicates of arbitrary arity to be covered within the description logic framework. The tableau algorithm provides a basis to implement a delayed grounding strategy which was not facilitated by earlier versions of decision procedures for satisfiability in expressive description logics with nominal schemas.

Reconciling Owl And Non-Monotonic Rules For The Semantic Web, Matthias Knorr, Pascal Hitzler, Frederick Maier

Computer Science and Engineering Faculty Publications

We propose a description logic extending SROIQ (the description logic underlying OWL 2 DL) and at the same time encompassing some of the most prominent monotonic and nonmonotonic rule languages, in particular Datalog extended with the answer set semantics. Our proposal could be considered a substantial contribution towards fulfilling the quest for a unifying logic for the Semantic Web. As a case in point, two non-monotonic extensions of description logics considered to be of distinct expressiveness until now are covered in our proposal. In contrast to earlier such proposals, our language has the 'look and feel' of a description logic …

Using Attribute Behavior Diversity To Build Accurate Decision Tree Committees For Microarray Data, Qian Han, Guozhu Dong

Kno.e.sis Publications

DNA microarrays (gene chips), frequently used in biological and medical studies, measure the expressions of thousands of genes per sample. Using microarray data to build accurate classifiers for diseases is an important task. This paper introduces an algorithm, called Committee of Decision Trees by Attribute Behavior Diversity (CABD), to build highly accurate ensembles of decision trees for such data. Since a committee's accuracy is greatly influenced by the diversity among its member classifiers, CABD uses two new ideas to "optimize" that diversity, namely (1) the concept of attribute behavior–based similarity between attributes, and (2) …

(Hidden) Social Influences In Switching Mobile Service Platforms, Virpi K. Tuunainen, Tuure Tuunanen, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

During the past few years, the mobile industry has gone through a radical change from business focusing on excellence in device manufacturing and supply chain management to ecosystems around successful focal players, such as Apple and Google, controlling these service platforms. In order to compete in this environment, these firms need to understand what makes a consumer switch between these mobile service platforms. To that end, we conducted an inductive qualitative study with university students from Finland and USA as subjects (142 altogether), delving into how and why consumers switch mobile phones, and what are the factors affecting their decisions. …

Twitris+: Social Media Analytics Platform For Effective Coordination, Gary Alan Smith, Amit P. Sheth, Ashutosh Sopan Jadhav, Hemant Purohit, Lu Chen, Michael Cooney, Pavan Kapanipathi, Pramod Anantharam, Pramod Koneru, Wenbo Wang

Kno.e.sis Publications

Twitris+ is a Semantic Social Media analytics platform to provide technologies for analyzing large-scale social media streams across Spatio-Temporal-Thematic (STT) and People-Content-Network (PCN) dimensions. It provides holistic situational awareness from one interface and enables organizational actors to engage in well-coordinated ways for desired tasks during emergency response.

Prosody-Based Query-By-Example Spoken Utterance Retrieval, Steven D. Werner, Nigel G. Ward

COURI Symposium Abstracts, Summer 2012

Current spoken dialogue retrieval systems are almost entirely lexically based, using automatic transcription by imperfect speech recognition technology. Once audio is reduced to text, little more than existing text search methods are used to retrieve results. However, spoken dialogue contains rich latent prosodic information about dialogue activities - such as agreeing, arguing, deciding, planning, storytelling, showing surprise - and this extra information can often be relevant to the searchers aims. Searching for similar speech acts rather then similar words enables similar contextual results, returning points where the speaker had the same sentiment during a topic. Previous research yielded 76 dimensions …

The Latent Maximum Entropy Principle, Shaojun Wang, Dale Schuurmans, Yunxin Zhao

Kno.e.sis Publications

We present an extension to Jaynes’ maximum entropy principle that incorporates latent variables. The principle of latent maximum entropy we propose is different from both Jaynes’ maximum entropy principle and maximum likelihood estimation, but can yield better estimates in the presence of hidden variables and limited training data. We first show that solving for a latent maximum entropy model poses a hard nonlinear constrained optimization problem in general. However, we then show that feasible solutions to this problem can be obtained efficiently for the special case of log-linear models---which forms the basis for an efficient approximation to the latent maximum …

What Kind Of #Communication Is Twitter? A Psycholinguistic Perspective On Communication In Twitter For The Purpose Of Emergency Coordination, Hemant Purohit, Andrew Hampton, Valerie L. Shalin, Amit P. Sheth, John Flach

Kno.e.sis Publications

The present research aims to detect coordinated citizen response within social media traffic to assist emergency response. We use domain-independent linguistic properties as the first step in narrowing the candidate set of messages for domain-dependent and computationally intensive analysis.

Exploring The Impact Of Knowledge And Social Environment On Influenza Prevention And Transmission In Midwestern United States High School Students, William L. Romine, Tanvi Banerjee, William S. Barrow, William R. Folk

Kno.e.sis Publications

We used data from a convenience sample of 410 Midwestern United States students from six secondary schools to develop parsimonious models for explaining and predicting precautions and illness related to influenza. Scores for knowledge and perceptions were obtained using two-parameter Item Response Theory (IRT) models. Relationships between outcome variables and predictors were verified using Pearson and Spearman correlations, and nested [student within school] fixed effects multinomial logistic regression models were specified from these using Akaike’s Information Criterion (AIC). Neural network models were then formulated as classifiers using 10-fold cross validation to predict precautions and illness. Perceived barriers against taking precautions …

Finding Bursty Topics From Microblogs, Qiming Diao, Jing Jiang, Feida Zhu, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Microblogs such as Twitter reflect the general public’s reactions to major events. Bursty topics from microblogs reveal what events have attracted the most online attention. Although bursty event detection from text streams has been studied before, previous work may not be suitable for microblogs because compared with other text streams such as news articles and scientific publications, microblog posts are particularly diverse and noisy. To find topics that have bursty patterns on microblogs, we propose a topic model that simultaneousy captures two observations: (1) posts published around the same time are more likely to have the same topic, and (2) …

Topic Discovery From Tweet Replies, Bingtian Dai, Ee Peng Lim, Philips Kokoh Prasetyo

Research Collection School Of Computing and Information Systems

Twitter is a popular online social information network service which allows people to read and post messages up to 140 characters, known as “tweets”. In this paper, we focus on the tweets between pairs of individuals, i.e., the tweet replies, and propose a generative model to discover topics among groups of twitter users. Our model has then been evaluated with a tweet dataset to show its effectiveness.

Detecting Anomalous Twitter Users By Extreme Group Behaviors, Hanbo Dai, Ee-Peng Lim, Feida Zhu, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Twitter has enjoyed tremendous popularity in the recent years. To help categorizing and search tweets, Twitter users assign hashtags to their tweets. Given that hashtag assignment is the primary way to semantically categorizing and search tweets, it is highly susceptible to abuse by spammers and other anomalous users [1]. Popular hashtags such as #Obama and #ladygaga could be hijacked by having them added to unrelated tweets with the intent of misleading many other users or promoting specific agenda to the users. The users performing this act are known as the hashtag hijackers. As the hijackers usually abuse common sets of …

Iexplore: A Provenance-Based Application For Exploring Biomedical Knowledge, Vinh Nguyen, Olivier Bodenreider, Thomas Rindflesch, Amit P. Sheth

Kno.e.sis Publications

No abstract provided.

W3c Semantic Sensor Networks: Ontologies, Applications, And Future Directions, Cory Andrew Henson

Kno.e.sis Publications

Plenary Talk discussing the W3C Semantic Sensor Network, including the ontology, applications, and future directions.

Topical Anomaly Detection From Twitter Streams, Pramod Anantharam, Krishnaprasad Thirunarayan, Amit P. Sheth

Kno.e.sis Publications

No abstract provided.