An improvement in the quality of expert finding in community question answering networks

2020 | Decision Support Systems | Citations: 1

Authors: Dehghan, Mahdi; Abin, Ahmad Ali; Neshati, Mahmood

Abstract: Expert finding in Community Question Answering (CQA) networks such as Stack Over ... Expand

Abstract: Expert finding in Community Question Answering (CQA) networks such as Stack Overflow is a practical issue facing a challenging problem called vocabulary gap. A widely used approach to overcome this problem is translation model. Different from prior works that only consider the relevancy of translations to a query, we intend to diversify query translations for better coverage of query topics. In this work, we have utilized the idea of clustering to group relevant translations to a given query into different clusters and then select representatives from each cluster as a set of diverse translations. We have proposed two new approaches to cluster translations. In the first one, the Mutual Information was primarily utilized as a similarity measure during clustering. In the second approach, the relevant translations are embedded in a topic space and then clustered in that space. After clustering, we propose two batch and sequential methods to select a diverse set of translations from the resultant clusters. The batch method selects the top most relevant translations from each cluster proportional to the rel­ evancy of that cluster to the user query. The sequential one is an iterative method that looks for the most diverse set of translations considering the previously selected ones. Finally, to rank users, a regression model was utilized to learn how expert and non-expert users differ in using a set of diverse translations in their documents. Ex­ periments on a large dataset generated from Stack Overflow demonstrate that the proposed methods improve the ranking performance over baselines in the expert finding. Collapse

Topics: PHP cloud computing Apache Lucene Java

Methods: cluster analysis experiment computational algorithm machine learning regression analysis method

An Ensemble of Ensembles Approach to Author Attribution for Internet Relay Chat Forensics

2020 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Shao, Sicong; Tunc, Cihan; Al-Shawi, Amany; Hariri, Salim

Abstract: With the advances in Internet technologies and services, social media has been g ... Expand

Abstract: With the advances in Internet technologies and services, social media has been gained extreme popularity, especially because these technologies provide potential anonymity, which in turn harbors hacker discussion forums, underground markets, dark web, and so on. Internet relay chat (IRC) is a real-time communication protocol actively used by cybercriminals for hacking, cracking, and carding. Hence, it is particularly urgent to identify the authors of threat messages and malicious activities in IRC. Unfortunately, author identification studies in IRC remain as an underexplored area. In this research, we perform novel IRC text feature extraction methods and propose the first author attribution version of the deep forest (DF) model that is an ensemble of ensembles that utilizes the fusion of ensemble learning techniques. Our approach is supported by autonomic IRC monitoring. Experiments show that our approach is highly effective for author attribution and attains high accuracy even when the number of candidates is large while training data is limited. Collapse

Topics: personality IT security social media data security anonymity

Methods: experiment support vector machine ensemble learning decision tree classification LightGBM

Theories: big five model

Learn or Earn? - Intelligent Task Recommendation for Competitive Crowdsourced Software Development

2018 | HICSS | Citations: 0

Authors: Karim, Muhammad Rezaul; Yang, Ye; Messinger, David; Ruhe, Guenther

Abstract: Background: Competitive crowdsourced development encourages online software deve ... Expand

Abstract: Background: Competitive crowdsourced development encourages online software developers to register for tasks offered on the crowdsourcing platform and implement them in a competitive mode. As a large number of tasks are uploaded daily, the scenery of competition is changing continuously. Without appropriate decision support, online developers often make task decisions in an ad hoc and intuitive manner. Aims: To provide dynamic decision support for crowd developers to select the task that fit best to their personal learning versus earning objectives, taking into account the actual competitiveness situation. Method: We propose a recommendation system called EX2 ("EX-Square") that combines both explorative ("learn") and exploitative ("earn") search for tasks, based on a systematic analysis of workers preference patterns, technologies hotness, and the projection of winning chances. The implemented prototype allows dynamic recommendations that reflect task updates and competition dynamics at any given time. Results: Based on evaluation from 4007 tasks monitored over a period of 2 years, we show that EX2 can explore and adjust task recommendations corresponding to context changes, and individual learning preferences of workers. A survey was also conducted with 14 actual crowd workers, showing that intelligent decision support from EX2 is considered useful and valuable. Conclusions: With support from EX2, workers benefit from the tool from getting customized recommendations, and the platform provider gets a higher chance to better cover the breadth of technology needs in case recommendations are taken. Collapse

Topics: recommender system Topcoder crowdsourcing application programming interface decision support

Methods: survey design artifact machine learning term frequency–inverse document frequency experiment

Counterfeit product detection: Bridging the gap between design science and behavioral science in information systems research

2017 | Decision Support Systems | Citations: 3

Authors: Wimmer, Hayden; Yoon, Victoria Y.

Abstract: In IS research, there is a dichotomy where design science and behavioral science ... Expand

Abstract: In IS research, there is a dichotomy where design science and behavioral science are distinct research paradigms. IS researchers should view these paradigms as complementary with research drawing upon the strengths of both, yet few have done so. This work demonstrates how design science and behavioral science can be united in IS research via counterfeit product detection based on product reviews in an online marketplace. Product authenticity in the online marketplace is a common issue plaguing consumers. The decision process involved in determining product authenticity is lengthy and complex. Despite the pressing need for an automatic authenticity rating system for online shopping, little research has been done to develop such a system and assess its effects on consumer purchase behavior. To respond to this need, our study develops a design artifact, called OnCDS, to automatically calculate the likelihood that a product is counterfeit based on online customer reviews. Drawing upon lexicon-based sentiment analysis approaches and TF-IDF as kernel theories for our design, we employ web scraping, natural language processing, and topic analysis methods to process customer reviews and calculate the counterfeit score of a product. In assessing the effects of OnCDS on consumer behavior, we develop a research model that encompasses trust and perceived risk based on the valence framework. Results show that our design artifact's efficacy is validated and that the counterfeit score affects perceived risk and trust, which in turn influences attitude toward purchase. Collapse

Topics: consumer behavior electronic market data quality information retrieval electronic commerce

Methods: design artifact sentiment analysis term frequency–inverse document frequency product review design science

Theories: information systems theory behavioral theory

The value of user’s Facebook profile data for product recommendation generation

2015 | Electronic Markets | Citations: 0

Authors: Heimbach, Irina; Gottschlich, Jörg; Hinz, Oliver

Abstract: Most online shops apply recommender systems, i.e. software agents that elicit th ... Expand

Abstract: Most online shops apply recommender systems, i.e. software agents that elicit the users’ preferences and interests with the purpose to make product recommendations. Many of these systems suffer from the new user cold start problem which occurs when no transaction history is available for the particular new prospective buyer. External data from social networking sites, like Facebook, seem promising to overcome this problem. In this paper, we evaluate the value of Facebook profile data to create meaningful product recommendations. We find based on the outcomes of a user experiment that already simple approaches and plain profile data matching yield significant better recommendations than a pure random draw from the product data base. However, the most successful approaches use semantic categories like music/video, brands and product category information to match profile and product data. A second experiment indicates that recommendation quality seems to be stable for different profile sizes. Collapse

Topics: Facebook recommender system social network database system experience good

Methods: experiment survey chi squared test hierarchical linear modeling longitudinal research

IT-Enabled Knowledge Creation for Open Innovation

2014 | Journal of the Association for Information Systems | Citations: 0

Authors: Eservel, U. Yeliz

Abstract: Open innovation is increasingly important for researchers and practitioners alik ... Expand

Abstract: Open innovation is increasingly important for researchers and practitioners alike. Open innovation is closely linked to knowledge creation in that, with open innovation, knowledge inflows and outflows are exploited for innovation. In the information systems field, open innovation has been closely linked to open source software development teams. However, the literature has not yet identified how open source software development teams use information technologies to create knowledge to bring about open innovation. This study fills in this gap by asking the following research questions: RQ1) How do innovative open source software development teams create knowledge?, and RQ2) What types of information technologies do innovative open source software development teams rely on for enabling knowledge creation? I answer these research questions with a revelatory case study. The findings contribute to the knowledge management theory by identifying how three of the four knowledge creation modes identified by Nonaka and Takeuchi (1995) manifest through different behaviors in the IT-enabled open innovation setting compared to behaviors observed in the organizational setting. The findings also contribute to information systems theory by identifying the role of information technologies in enabling knowledge creation for open innovation. This study further provides researchers and practitioners with ways of identifying knowledge creation by analyzing information technology artifacts, such as mailing lists, issue trackers, and software versioning tools. Collapse

Topics: knowledge creation open source open innovation innovation management Apache Lucene

Methods: qualitative content analysis archival research design artifact case study field study

Theories: knowledge management theory information systems theory

Leadership in a Non-Traditional Setting: Self-Managing Virtual IS Development Teams

2009 | International Conference on Information Systems | Citations: 0

Authors: Eseryel, U Yeliz

Abstract: Despite its abundance, traditional leadership research cannot be claimed to tran ... Expand

Abstract: Despite its abundance, traditional leadership research cannot be claimed to transfer directly to the leadership context of self-managing virtual (SMV) Information Systems Development teams. Unique conditions of these novel team environments require focused studies of leadership in virtual team settings. Although there are some studies of virtual team leadership that make important contributions to the literature, these studies typically use short term, ad-hoc teams of students. This study ultimately aims at filling the gap in the literature by investigating how leadership manifests in real-life SMV IS teams over time. In this paper, the overall study is introduced and the initial findings based on the content analysis schema development effort are reported. Collapse

Topics: systems development electronic mail boundary spanning Java Apache Lucene

Methods: qualitative interview archival research qualitative content analysis field study case study

Theories: leadership theory

Semantically Enhanced Passage Retrieval for Business Analysis Activity

2008 | European Conference On Information Systems | Citations: 0

Authors: Thai, VinhTuan

Abstract: Business analysis activity often involves the identification and extraction of i ... Expand

Abstract: Business analysis activity often involves the identification and extraction of information from business reports. The unstructured content of business reports poses a challenge to current Business Intelligence technologies. In this paper, we present an application that provides passage retrieval capability, which has been developed for use in business analysis activity at Hewlett-Packard™ (HP). Preliminary evaluation of the application indicates that the inclusion of domain knowledge such as domain semantics and business intelligence rules plays an important part in system performance. It dramatically reduces the time that analysts spend extracting relevant informative passages within a report or business intelligence. In addition, it can find further relevant information that would have been overlooked by the analyst. Collapse

Topics: knowledge representation business intelligence Apache Lucene search engine business model

Methods: design artifact domain ontology ontological modelling question answering literature study