Nargis Pervin

With the increased popularity of the smart mobile devices, mobile applications (a.k.a apps) have become essential. While the app developers face an extensive challenge to improve user satisfaction by exploiting the valuable feedbacks, the app users are overloaded with way too many apps. Extracting the valuable features from apps and mining the associated sentiments is of utmost importance for the app developers. Similarly, from the user perspective, the key preferences should be identified. This work deals with profiling users and apps using a novel LDA based aspect identification technique. Polarity aggregation technique is used to tag the weak features of the apps the developers should concentrate on. The proposed technique has been experimented on an Android review dataset to validate the efficacy compared to state-of-the-art algorithms. Experimental findings suggest superiority and applicability of our model in practical scenarios.

A systematic review of literature is a crucial aspect in pursuing any research problem. With the galloping growth in the number of researchers and scientific publications available online in digital libraries, there is information overload which makes the search of relevant papers cumbersome. An efficient academic paper recommendation process could be a promising maneuver for this purpose. The state-of-the-art methods in this domain primarily employ link-based approaches on citation network and do not consider the semantics (context) of papers being recommended, although the later one largely accounts for the relevance of recommendations. Also achieving online response time (scalability) is a perennial desire for any recommendation system. In this context we propose a hybrid approach 'RecCite' that blends the popularity of papers with semantic similarity to acquire relevance. Further, the approach follows a top-down methodology for filtering papers from a more generic and larger network to a community pertaining to a SIG (Special Interest Group) that inherently addresses the scalability aspect. The proposed approach has been systematically evaluated with state-of-the-art baseline method using the publicly available Arnet-Miner data set. Satisfyingly, 'RecCite' outperforms the baseline method with up to 37.66%, 20.14%, and 97.24% improvement in precision, recall, and response time, respectively.

Even with the rapid proliferation of applications (“apps”) running on smart handheld devices, achieving success in mobile platform ecosystems is challenging for developers because of the heavily crowded marketplaces and easy substitutability of apps. In this study, we draw inspiration from biological ecosystems research and from the operations management literatures on software production, product management, and digital platforms to empirically examine the sustainability of newly launched apps in the Apple and Google mobile platform ecosystems. In the ecology literature, a “habitat trap” refers to the instinctive but detrimental behavioral response which can potentially lead to the extinction of organisms facing dynamic changes in their habitats. Applying the habitat traps concept to mobile platform ecosystems, we investigate whether seemingly beneficial actions of app developers can indeed become detrimental to the sustainability of their apps. Using lifecycle data of 57,117 newly launched paid apps, we examine the impact of five developer actions (updating the apps, offering price promotions, and diversifying into functional variants, similar apps, and other platforms) on the sustainability of the apps. The results of our analysis show that while frequent app updates are beneficial, engaging in price promotions and diversification-oriented activities indeed have the risks of turning into traps for developers. We utilize the empirical results to draw attention to the heterogeneity of traps in mobile platform ecosystems, shed light on the need to develop strategies for overcoming the traps, and discuss the implications of the presence of platform traps for emerging theories on digital ecosystems.

Recently, a new paradigm of social network based recommendation approach has emerged wherein structural features from social network turned out to be an effective measure to improve the efficacy of the algorithms. However, these approaches assume a user is impacted by all his social connections and completely ignore their preferential similarity, which is crucial for personalized recommendations. Herein, we address this pivotal issue and propose a two-stage clustering based matrix-factorization algorithm, "Cluster REfinement on Preference Embedded MF (CREPE MF)" using a subgraph of social network that integrates the preferential similarity score. Clustering has been applied first on the user followed by the item based on ratings. The proposed algorithm has been systematically evaluated with state-of-the-art algorithms in terms of prediction accuracy and runtime complexity using real-world Yelp dataset. Gratifyingly, our approach outperforms the state-of-the-art algorithms with up to 12.97% and 29.60% improvements in RMSE and runtime, respectively.

The COVID-19 pandemic has plunged the world into chaos by affecting people's lifestyles and imposing immense pressures on healthcare professionals. Since its outbreak in Wuhan, China, back in December 2019, researchers all across the globe have been working tirelessly to provide reliable insights to understand and combat the virus. As a result, the number of publications related to the novel coronavirus has been increasing rapidly. This study aims to quantify and summarize the progress of SARS-CoV-2 related research from November 2019 onwards to January 2021 by employing a bibliometric analysis and topic modelling approaches. A total of 33,159 research publications, downloaded from the Web of Science (WoS) core collection database, were analyzed. The key aspects of our study include identifying important publications, their distribution across countries and organizations, important journals and central authors who have made a significant contribution to the current literature. We have also delineated the major themes addressed in the academic community.

With the advent of Web 2.0, recommender systems have become a viable means to harness relevant information online. In the past decades, extensive research have been conducted in the field of recommendations — model-based collaborative techniques being the most favored ones. Recently, a new paradigm of trust-based recommendation approach has emerged wherein structural features from social network resulted in an improved efficacy of the algorithms. However, majority of these approaches assume that users' ratings are impacted by all his social connections in friendship network and completely ignore their preferential similarity, which is essential for personalized recommendations. Herein, we address this pivotal issue and propose a two-stage clustering based matrix-factorization algorithm, ‘Cluster REfinement on Preference Embedded MF (CREPE MF)’ using a subgraph of social network that integrates preferential similarity score. Also, an immense surge in mobile device usage has been observed in recent times, thereby paving the way for tracking users' locations en-route to physical entity recommendations. As users' locations are geo-spatially co-located, we extend CREPE MF to Geographical CREPE MF (gCREPE MF) by incorporating geo-spatial influence. These two proposed algorithms have been systematically evaluated with state-of-the-art algorithms in terms of prediction accuracy and runtime complexity using two real-world data sets, namely Yelp and Gowalla. Gratifyingly, our approach CREPE MF outperforms the state-of-the-art algorithms; depending on the underlying data sets it achieves an improvement of 6.50% to 17.93% in accuracy and 11.67% to 74.23% in runtime. Extended model gCREPE MF further achieves 18.06% to 83.44% reduction in runtime without compromising on accuracy.

The accelerated growth of the Web2.0 has led to an abundance of accessible information which has been successfully harnessed by many researchers for personalizing products and services. Many personalization algorithms are focused on analyzing only the explicitly provided information and this limits the scope for a deeper understanding of the individuals’ preferences. However, analyzing the reviews posted by the users seeks to provide a better understanding of users’ personal preferences and also aids in uncovering business’ strengths and weaknesses as perceived by the users. Topic Modeling, a popular machine learning technique addresses this issue by extracting the underlying abstract topics in the textual data. In this study, we present entity-LDA (eLDA), a variation of Latent Dirichlet Allocation for topic modeling along with a dependency tree based aspect level sentiment analysis methodology for constructing user and business profiles. We conduct several experiments for evaluating the quantitative and qualitative performance of our proposed model compared to state-of-the-art methods. Experimental results demonstrate the efficacy of our proposed method both in terms topic quality and interpretability. Finally we develop a framework for constructing user and business profiles from the topic probabilities. Further we enhance the business profiles by extracting syntactic aspect level sentiments to indicate sentimental polarity for each aspects.

Wicked problems are embedded with attributes such as lack of understanding, multiple stakeholders’ involvement in solution implementation and the lack of opportunity of undoing the solution implemented. Hence, a robust methodology is required to understand its nature. Interactive Qualitative Analysis (IQA) is a systems method that caters to the need of understanding the phenomenon while also provisioning means to understand different stakehold-ers’ perceptions of the phenomenon. This study demonstrates the use of IQA in understanding a wicked problem in healthcare sector dealing with patients’ internet usage. Our analysis reveals that patients elicit the need of the internet in three new realms, namely, hospital choice, physician choice, and online support services, which were not apparent in previous studies on the same context. The study’s findings provide insights that could lead to development of strategies for meta-services within healthcare sector involving information dissemination for patients through the internet.

The growing popularity of digital libraries as a medium for communicating scientific discoveries has made a large variety of research articles easily accessible. However, this constitutes a putative issue of information overloading with recommendation engines providing a compelling solution to the problem. Scientific Recommender Systems alleviate this problem by suggesting potential papers of interest to a user. For any researcher seeking developments in their field, it is important that the recommended papers are of high quality, recent and related to the field of interest, which has been largely overlooked in prior approaches. This study thus proposes a graph-based hybrid recommendation technique, SPACE-R, that amalgamates quality, semantic similarity and community structure of nodes in a citation network. The creation of a popularity network, a derivative of a citation network, in combination with a two-stage candidate selection process involving community detection and neighbourhood network identification, contributes to an improvement in the accuracy and scalability of the proposed model. The incorporation of semantic similarity achieves the necessary diversity in recommendations. Experimental evaluations on four large datasets against five baselines reveal that SPACE-R achieves an improvement of up to 45.53%, 56.76%, 49.39%, 46.84% and 78.18% in recall, precision, MRR, mAP, and response time, respectively.