Digital Commons Network^™

Evaluation And Improvement Of Procurement Process With Data Analytics, Melvin H. C. Tan, Wee Leong Lee

Research Collection School Of Computing and Information Systems

Analytics can be applied in procurement to benefit organizations beyond just prevention and detection of fraud. This study aims to demonstrate how advanced data mining techniques such as text mining and cluster analysis can be used to improve visibility of procurement patterns and provide decision-makers with insight to develop more efficient sourcing strategies, in terms of cost and effort. A case study of an organization’s effort to improve its procurement process is presented in this paper. The findings from this study suggest that opportunities exist for organizations to aggregate common goods and services among the purchases made under and across …

Developing Java Programs On Android Mobile Phones Using Speech Recognition, Santhrushna Gande

Electronic Theses, Projects, and Dissertations

Nowadays Android operating system based mobile phones and tablets are widely used and had millions of users around the world. The popularity of this operating system is due to its multi-tasking, ease of access and diverse device options. “Java Programming Speech Recognition Application” is an Android application used for handicapped individuals who are not able or have difficultation to type on a keyboard. This application allows the user to write a compute program (in Java Language) by dictating the words and without using a keyboard. The user needs to speak out the commands and symbols required for his/her program. The …

Did You Expect Your Users To Say This?: Distilling Unexpected Micro-Reviews For Venue Owners, Wen-Haw Chong, Bingtian Dai, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

With social media platforms such as Foursquare, users can now generate concise reviews, i.e. micro-reviews, about entities such as venues (or products). From the venue owner's perspective, analysing these micro-reviews will offer interesting insights, useful for event detection and customer relationship management. However not all micro-reviews are equally important, especially since a venue owner should already be familiar with his venue's primary aspects. Instead we envisage that a venue owner will be interested in micro-reviews that are unexpected to him. These can arise in many ways, such as users focusing on easily overlooked aspects (by the venue owner), making comparisons …

Name List Only? Target Entity Disambiguation In Short Texts, Yixin Cao, Juanzi Li, Xiaofei Guo, Shuanhu Bai, Heng Ji, Jie Tang

Research Collection School Of Computing and Information Systems

Target entity disambiguation (TED), the task of identifying target entities of the same domain, has been recognized as a critical step in various important applications. In this paper, we propose a graphbased model called TremenRank to collectively identify target entities in short texts given a name list only. TremenRank propagates trust within the graph, allowing for an arbitrary number of target entities and texts using inverted index technology. Furthermore, we design a multi-layer directed graph to assign different trust levels to short texts for better performance. The experimental results demonstrate that our model outperforms state-of-the-art methods with an average gain …

Using Content-Level Structures For Summarizing Microblog Repost Trees, Jing Li, Wei Gao, Zhongyu Wei, Baolin Peng, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

A microblog repost tree provides strong clues on how an event described therein develops. To help social media users capture the main clues of events on microblogging sites, we propose a novel repost tree summarization framework by effectively differentiating two kinds of messages on repost trees called leaders and followers, which are derived from contentlevel structure information, i.e., contents of messages and the reposting relations. To this end, Conditional Random Fields (CRF) model is used to detect leaders across repost tree paths. We then present a variant of random-walk-based summarization model to rank and select salient messages based on the …

Towards Opinion Summarization From Online Forums, Ding Ying, Jing Jiang

Research Collection School Of Computing and Information Systems

Summarizing opinions expressed in online forums can potentially benefit many people. However, special characteristics of this problem may require changes to standard text summarization techniques. In this work, we present our initial attempt at extractive summarization of opinionated online forum threads. Given the nature of user generated content in online discussion forums, we hypothesize that besides relevance, text quality and subjectivity also play important roles in deciding which sentences are good summary sentences. We therefore construct an annotated corpus to facilitate our study of extractive summarization of online discussion forums. We define a set of features to capture relevance, text …

A Joint Model Of Product Properties, Aspects And Ratings For Online Reviews, Ding Ying, Jing Jiang

Research Collection School Of Computing and Information Systems

Product review mining is an important task that can benefit both businesses and consumers. Lately a number of models combining collaborative filtering and content analysis to model reviews have been proposed, among which the Hidden Factors as Topics (HFT) model is a notable one. In this work, we propose a new model on top of HFT to separate product properties and aspects. Product properties are intrinsic to certain products (e.g. types of cuisines of restaurants) whereas aspects are dimensions along which products in the same category can be compared (e.g. service quality of restaurants). Our proposed model explicitly separates the …

Using Content-Level Structures For Summarizing Microblog Repost Trees, Jing Li, Wei Gao, Zhongyu Wei, Baolin Peng, Kam-Fai Wong

Research Collection School Of Computing and Information Systems

A microblog repost tree provides strong clues on how an event described therein develops. To help social media users capture the main clues of events on microblogging sites, we propose a novel repost tree summarization framework by effectively differentiating two kinds of messages on repost trees called leaders and followers, which are derived from contentlevel structure information, i.e., contents of messages and the reposting relations. To this end, Conditional Random Fields (CRF) model is used to detect leaders across repost tree paths. We then present a variant of random-walk-based summarization model to rank and select salient messages based on the …

Fuzzy Logic-Based Guaranteed Lifetime Protocol For Real-Time Wireless Sensor Networks, Babar Shah, Farkhund Iqbal, Ali Abbas, Ki Il Kim

All Works

© 2015 by the authors; licensee MDPI, Basel, Switzerland. Few techniques for guaranteeing a network lifetime have been proposed despite its great impact on network management. Moreover, since the existing schemes are mostly dependent on the combination of disparate parameters, they do not provide additional services, such as real-time communications and balanced energy consumption among sensor nodes; thus, the adaptability problems remain unresolved among nodes in wireless sensor networks (WSNs). To solve these problems, we propose a novel fuzzy logic model to provide real-time communication in a guaranteed WSN lifetime. The proposed fuzzy logic controller accepts the input descriptors energy, …

A Study On The Efficacy Of Sentiment Analysis In Author Attribution, Michael J. Schneider

Electronic Theses and Dissertations

The field of authorship attribution seeks to characterize an author’s writing style well enough to determine whether he or she has written a text of interest. One subfield of authorship attribution, stylometry, seeks to find the necessary literary attributes to quantify an author’s writing style. The research presented here sought to determine the efficacy of sentiment analysis as a new stylometric feature, by comparing its performance in attributing authorship against the performance of traditional stylometric features. Experimentation, with a corpus of sci-fi texts, found sentiment analysis to have a much lower performance in assigning authorship than the traditional stylometric features.

Faitcrowd: Fine Grained Truth Discovery For Crowdsourced Data Aggregation, Fenglong Ma, Yaliang Li, Qi Li, Minghui Qiu, Jing Gao, Shi Zhi, Lu Su, Bo Zhao, Jiawei Han

Research Collection School Of Computing and Information Systems

In crowdsourced data aggregation task, there exist conflicts in the answers provided by large numbers of sources on the same set of questions. The most important challenge for this task is to estimate source reliability and select answers that are provided by high-quality sources. Existing work solves this problem by simultaneously estimating sources' reliability and inferring questions' true answers (i.e., the truths). However, these methods assume that a source has the same reliability degree on all the questions, but ignore the fact that sources' reliability may vary significantly among different topics. To capture various expertise levels on different topics, we …

Long-Term Study Of Crowdfunding Platform: Predicting Project Success And Fundraising Amount, Jinwook Chung

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Crowdfunding that is the combination word of crowdsourcing and funding makes people can start a business easily. Legislating JOBS act in US played a major role in removing restricted barriers of crowdfunding on public offerings of fence and private funds for small business. The growth speed of crowdfunding takes some beating. Through Kickstarter that is a popular crowdfunding platform and being considered the typical case of crowdfunding, 480 million dollars and more than half a billion dollars were invested in about 19 thousand and 22 projects for 2013 and 2014 respectively. But in spite of the rapid growth, the successful …

Detecting Experts On Quora: By Their Activity, Quality Of Answers, Linguistic Characteristics And Temporal Behaviors, Sumanth Kumar Reddy Nagarur Patil

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Question and answering sites are useful in sharing the knowledge by answering questions. It is a medium of sharing knowledge. Quora is the fastest emerging effective Q&A site, which is the best source of knowledge. Here you can ask a question, and get help in getting answers from people with firsthand experience, and blog about what you know. In this paper, we are investigating and identifying potential experts who are providing the best solutions to the questioner needs. We have considered several techniques in identifying user as an expert or non-expert. We have targeted the most followed topics in Quora …

Tweet Sentiment: From Classification To Quantification, Wei Gao, Fabrizio Sebastiani

Research Collection School Of Computing and Information Systems

Sentiment classification has become a ubiquitous enabling technology in the Twittersphere, since classifying tweets according to the sentiment they convey towards a given entity (be it a product, a person, a political party, or a policy) has many applications in political science, social science, market research, and many others. In this paper we contend that most previous studies dealing with tweet sentiment classification (TSC) use a suboptimal approach. The reason is that the final goal of most such studies is not estimating the class label (e.g., Positive, Negative, or Neutral) of individual tweets, but estimating the relative frequency (a.k.a. "prevalence") …

Gibberish, Assistant, Or Master? Using Tweets Linking To News For Extractive Single-Document Summarization, Zhongyu Wei, Wei Gao

Research Collection School Of Computing and Information Systems

Single-document summarization is a challenging task. In this paper, we explore effective ways using the tweets linking to news for generating extractive summary of each document. We reveal the very basic value of tweets that can be utilized by regarding every tweet as a vote for candidate sentences. Base on such finding, we resort to unsupervised summarization models by leveraging the linking tweets to master the ranking of candidate extracts via random walk on a heterogeneous graph. The advantage is that we can use the linking tweets to opportunistically "supervise" the summarization with no need of reference summaries. Furthermore, we …

Data Analysis With Map Reduce Programming Paradigm, Mandana Bozorgi

UNLV Theses, Dissertations, Professional Papers, and Capstones

Abstract In this thesis, we present a summary of our activities associated with the storage and query processing of Google 1T 5-gram data set. We rst give a brief introduction to some of the implementation techniques for the relational algebra followed by a Map Reduce implementation of the same operators. We then implement a database schema in Hive for the Google 1T 5-gram data set.

The thesis will further look into the query processing with Hive and Pig in the Hadoop setting.

More specially, we report statistics for our queries in this environment.

Topic Modeling With Document Relative Similarities, Jianguang Du, Jing Jiang, Dandan Song, Lejian Liao

Research Collection School Of Computing and Information Systems

Topic modeling has been widely used in text mining. Previous topic models such as Latent Dirichlet Allocation (LDA) are successful in learning hidden topics but they do not take into account metadata of documents. To tackle this problem, many augmented topic models have been proposed to jointly model text and metadata. But most existing models handle only categorical and numerical types of metadata. We identify another type of metadata that can be more natural to obtain in some scenarios. These are relative similarities among documents. In this paper, we propose a general model that links LDA with constraints derived from …

Growing The Practice Of Vocal Sketching, S. Delle Monache, D. Rocchesso, S. Baldan, Davide Andrea Mauro Phd

Computer Sciences and Electrical Engineering Faculty Research

Sketch-thinking in the design domain is a complex representational activity, emerging from the reflective conversation with the sketch. A recent line of research on computational support for sound design has been focusing on the exploitation of voice, and especially vocal imitations, as effective representation strategy for the early stage of the design process. A set of introductory exercises on vocal sketching, to probe the communication effectiveness of vocal imitations for design purposes, are presented and discussed, in the scope of the research-through-design workshop activities of the EU project SkAT-VG.

Mwp-Bert: Numeracy-Augmented Pre-Training For Math Word Problem Solving, Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, Xiangliang Zhang

Student Publications

Math word problem (MWP) solving faces a dilemma in number representation learning. In order to avoid the number representation issue and reduce the search space of feasible solutions, existing works striving for MWP solving usually replace real numbers with symbolic placeholders to focus on logic reasoning. However, different from common symbolic reasoning tasks like program synthesis and knowledge graph reasoning, MWP solving has extra requirements in numerical reasoning. In other words, instead of the number value itself, it is the reusable numerical property that matters more in numerical reasoning. Therefore, we argue that injecting numerical properties into symbolic placeholders with …

Missing Photos, Suffering Withdrawal, Or Finding Freedom? How Experiences Of Social Media Non-Use Influence The Likelihood Of Reversion, Eric P.S. Baumer, Shion Guha, Emily Quan, David Mimno, Geri K. Gay

Mathematics, Statistics and Computer Science Faculty Research and Publications

This article examines social media reversion, when a user intentionally ceases using a social media site but then later resumes use of the site. We analyze a convenience sample of survey data from people who volunteered to stay off Facebook for 99 days but, in some cases, returned before that time. We conduct three separate analyses to triangulate on the phenomenon of reversion: simple quantitative predictors of reversion, factor analysis of adjectives used by respondents to describe their experiences of not using Facebook, and statistical topic analysis of free-text responses. Significant factors predicting either increased or decreased likelihood of reversion …

Automatic User Profile Construction For A Personalized News Recommender System Using Twitter, Shiva Theja Reddy Gopidi

Graduate Theses and Dissertations

Modern society has now grown accustomed to reading online or digital news. However, the huge corpus of information available online poses a challenge to users when trying to find relevant articles. A hybrid system “Personalized News Recommender Using Twitter’ has been developed to recommend articles to a user based on the popularity of the articles and also the profile of the user. The hybrid system is a fusion of a collaborative recommender system developed using tweets from the “Twitter” public timeline and a content recommender system based the user’s past interests summarized in their conceptual user profile. In previous work, …

Using Tweets To Help Sentence Compression For News Highlights Generation, Zhongyu Wei, Yang Liu, Chen Li, Wei Gao

Research Collection School Of Computing and Information Systems

We explore using relevant tweets of a given news article to help sentence compression for generating compressive news highlights. We extend an unsupervised dependency-tree based sentence compression approach by incorporating tweet information to weight the tree edge in terms of informativeness and syntactic importance. The experimental results on a public corpus that contains both news articles and relevant tweets show that our proposed tweets guided sentence compression method can improve the summarization performance significantly compared to the baseline generic sentence compression method.

Solar: Scalable Online Learning Algorithms For Ranking, Jialei Wang, Ji Wan, Yongdong Zhang, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Traditional learning to rank methods learn ranking models from training data in a batch and offline learning mode, which suffers from some critical limitations, e.g., poor scalability as the model has to be retrained from scratch whenever new training data arrives. This is clearly nonscalable for many real applications in practice where training data often arrives sequentially and frequently. To overcome the limitations, this paper presents SOLAR- a new framework of Scalable Online Learning Algorithms for Ranking, to tackle the challenge of scalable learning to rank. Specifically, we propose two novel SOLAR algorithms and analyze their IR measure bounds theoretically. …

Estimating Effectiveness Of Twitter Messages With A Personalized Machine Learning Approach, Xunhu Sun

Theses and Dissertations

In Twitter, many aspects of retweeting behavior, which is the most effective indicator of spreading effectiveness of the tweet, have been researched, such as whether a reader will retweet a certain tweet or not. However, the total number of retweets of the tweet, which is the quantitative measure of quality, has not been well addressed by existing work. To estimate the number of retweets and associated factors, this paper proposes a procedure to develop a personalized model for one author. The training data comes from the author’s past tweets. We propose 3 types of new features based on the contents …

A Hassle-Free Unsupervised Domain Adaptation Method Using Instance Similarity Features, Jianfei Yu, Jing Jiang

Research Collection School Of Computing and Information Systems

We present a simple yet effective unsupervised domain adaptation method that can be generally applied for different NLP tasks. Our method uses unlabeled target domain instances to induce a set of instance similarity features. These features are then combined with the original features to represent labeled source domain instances. Using three NLP tasks, we show that our method consistently out-performs a few baselines, including SCL, an existing general unsupervised domain adaptation method widely used in NLP. More importantly, our method is very easy to implement and incurs much less computational cost than SCL.

A Convolution Kernel Approach To Identifying Comparisons In Text, Maksim Tkachenko, Hady W. Lauw

Research Collection School Of Computing and Information Systems

Comparisons in text, such as in online reviews, serve as useful decision aids. In this paper, we focus on the task of identifying whether a comparison exists between a specific pair of entity mentions in a sentence. This formulation is transformative, as previous work only seeks to determine whether a sentence is comparative, which is presumptuous in the event the sentence mentions multiple entities and is comparing only some, not all, of them. Our approach leverages not only lexical features such as salient words, but also structural features expressing the relationships among words and entity mentions. To model these features …

Consciousness-Raising, Error Correction And Proofreading., Josephine O'Brien

All Works

The paper discusses the impact of developing a consciousness-raising approach in error correction at the sentence level to improve students' proofreading ability. Learners of English in a foreign language environment often rely on translation as a composing tool and while this may act as a scaffold and provide some support, it frequently leads to predictable and persistent errors. Such fossilization can cause inaccuracies that detract from student composition and that require instruction and repeated practice in order to eradicate the errors. The current paper reports on an experiment in consciousness-raising about specific categories of errors with a group of 30 …

Qcri: Answer Selection For Community Question Answering - Experiment For Arabic And English, Massimo Nicosia, Simone Filice, Alberto Barron-Cedeno, Iman Saleh, Hamdy Mubarak, Wei Gao, Preslav Nakov, Giovanni Da San Martino, Alessandro Moschitti, Kareem Darwish, Lluis Marquz Marquz, Shafiq Joty, Walid Magdy Magdy

Research Collection School Of Computing and Information Systems

This paper describes QCRI’s participation in SemEval-2015 Task 3 “Answer Selection in Community Question Answering”, which targeted real-life Web forums, and was offered in both Arabic and English. We apply a supervised machine learning approach considering a manifold of features including among others word n-grams, text similarity, sentiment analysis, the presence of specific words, and the context of a comment. Our approach was the best performing one in the Arabic subtask and the third best in the two English subtasks

Technical Communication As Teaching: A Grounded Theory Study Of Cognitive Empathy And Audience Engagement Among Computer Science Majors In A Technical Communication Classroom, Robert Michael Rowan

Theses and Dissertations

This dissertation is a grounded theory study of empathy, ethical awareness, and audience engagement activities in students in a technical writing service course. The course was designed around an empathy-oriented approach to teaching technical writing and writing research. The students are primarily computer science majors, and the teaching methods include a genre and writing research approach as well as the use of an extended metaphor of technical communication as a form of teaching. Findings indicate that students respond to the metaphor by drawing upon positive and empathetically-informed models of teachers and teaching to guide how they would work with and …

When Should We Switch From Interval-Valued Fuzzy To Full Type-2 Fuzzy (E.G., Gaussian)?, Vladik Kreinovich, Chrysostomos D. Stylios

Departmental Technical Reports (CS)

Full type-2 fuzzy techniques provide a more adequate representation of expert knowledge. However, such techniques also require additional computational efforts, so we should only use them if we expect a reasonable improvement in the result of the corresponding data processing. It is therefore important to come up with a practically useful criterion for deciding when we should stay with interval-valued fuzzy and when we should use full type-2 fuzzy techniques. Such a criterion is proposed in this paper. We also analyze how many experts we need to ask to come up with a reasonable description of expert uncertainty.