Lakshmi Ramachandran

Bio: Lakshmi Ramachandran is an academic researcher from North Carolina State University. The author has contributed to research in topics: Graph (abstract data type) & Technical peer review. The author has an hindex of 8, co-authored 21 publications receiving 212 citations. Previous affiliations of Lakshmi Ramachandran include Amazon.com & Pearson Education.

Dynamic resource demand prediction and allocation in multi-tenant service clouds

Abstract: Cloud computing is emerging as an increasingly popular computing paradigm, allowing dynamic scaling of resources available to users as needed This requires a highly accurate demand prediction and resource allocation methodology that can provision resources in advance, thereby minimizing the virtual machine downtime required for resource provisioning In this paper, we present a dynamic resource demand prediction and allocation framework in multi-tenant service clouds The novel contribution of our proposed framework is that it classifies the service tenants as per whether their resource requirements would increase or not; based on this classification, our framework prioritizes prediction for those service tenants in which resource demand would increase, thereby minimizing the time needed for prediction Furthermore, our approach adds the service tenants to matched virtual machines and allocates the virtual machines to physical host machines using a best-fit heuristic approach Performance results demonstrate how our best-fit heuristic approach could efficiently allocate virtual machines to hosts so that the hosts are utilized to their fullest capacity Copyright © 2016 John Wiley & Sons, Ltd

Identifying Patterns For Short Answer Scoring Using Graph-based Lexico-Semantic Text Matching

Abstract: Short answer scoring systems typically use regular expressions, templates or logic expressions to detect the presence of specific terms or concepts among student responses. Previous work has shown that manually developed regular expressions can provide effective scoring, however manual development can be quite time consuming. In this work we present a new approach that uses word-order graphs to identify important patterns from humanprovided rubric texts and top-scoring student answers. The approach also uses semantic metrics to determine groups of related words, which can represent alternative answers. We evaluate our approach on two datasets: (1) the Kaggle Short Answer dataset (ASAP-SAS, 2012), and (2) a short answer dataset provided by Mohler et al. (2011). We show that our automated approach performs better than the best performing Kaggle entry and generalizes as a method to the Mohler dataset.

Automated Assessment of the Quality of Peer Reviews using Natural Language Processing Techniques

Abstract: A review is textual feedback provided by a reviewer to the author of a submitted version. Peer reviews are used in academic publishing and in education to assess student work. While reviews are important to e-commerce sites like Amazon and e-bay, which use them to assess the quality of products and services, our work focuses on academic reviewing. We seek to help reviewers improve the quality of their reviews. One way to measure review quality is through metareview or review of reviews. We develop an automated metareview software that provides rapid feedback to reviewers on their assessment of authors’ submissions. To measure review quality, we employ metrics such as: review content type, review relevance, review’s coverage of a submission, review tone, review volume and review plagiarism (from the submission or from other reviews). We use natural language processing and machine-learning techniques to calculate these metrics. We summarize results from experiments to evaluate our review quality metrics: review content, relevance and coverage, and a study to analyze user perceptions of importance and usefulness of these metrics. Our approaches were evaluated on data from Expertiza and the Scaffolded Writing and Rewriting in the Discipline (SWoRD) project, which are two collaborative web-based learning applications.

Automated Assessment of Review Quality Using Latent Semantic Analysis

Abstract: Quality of a review can be identified by reviewing a review. Quantifiable factors that help identify the quality of a review include quality and tone of review comments, and the number of tokens each contains. We use machine-learning techniques such as latent semantic analysis (LSA) and cosine similarity to classify comments based on their quality and tone. Our paper details experiments that were conducted on student review and metareview data by using different data pre-processing steps. We compare these pre-processing steps and show that when applied to student review data, they help improve data quality by providing better text classification. Our technique helps predict metareview scores for student reviews.

Dynamic provisioning in multi-tenant service clouds

Abstract: Cloud-based systems promise an on-demand service provisioning system along with a “pay-as-you-use” policy. In the case of multi-tenant systems this would mean dynamic creation of a tenant by integrating existing cloud-based services on the fly. Presently, dynamic creation of a tenant is handled by building the required components from scratch. Although multi-tenant systems help providers save cost by allocating multiple tenants to the same instance of an application, they incur huge reconfiguration costs. Cost and time spent on these reconfiguration activities can be reduced by re-constructing tenants from existing tenant configurations supported by service providers. Multi-tenant cloud-based systems also lack the facility of allowing clients to specify their requirements. Giving clients the flexibility to specify requirements helps them avoid spending an excessive amount of time and effort looking through a list of services, many of which might not be relevant to them. Moreover, dynamic provisioning in the cloud requires an integrated solution across the technology stack (software, platform and infrastructure) combining functional, non-functional and resource allocation requirements. Existing research works in the area of web service matching, although numerous, still fall short, since they usually consider each requirement type in isolation and cannot provide an integrated solution. To that end, in this paper we investigate the features needed for dynamic service provisioning on the cloud. We propose a novel User Interface-Tenant Selector-Customizer (UTC) model and approach, which enables cloud-based services to be systematically modeled and provisioned as variants of existing service tenants in the cloud. Our approach considers functional, non-functional and resource allocation requirements, which are explicitly specified by the client via the user interface component of the model. To the best of our knowledge, ours is the first such integrated approach. We illustrate our ideas using a realistic running example, and also present a proof-of-concept prototype built using IBM’s Rational Software Architect modeling tool. We also present experimental results demonstrating the applicability of our matching algorithm. Our results show significant reduction in matching time with the help of an elimination process that reduces the search space needed for performing matching.

Sentiment analysis of twitter data using machine learning approaches and semantic analysis

Abstract: The wide spread of World Wide Web has brought a new way of expressing the sentiments of individuals. It is also a medium with a huge amount of information where users can view the opinion of other users that are classified into different sentiment classes and are increasingly growing as a key factor in decision making. This paper contributes to the sentiment analysis for customers' review classification which is helpful to analyze the information in the form of the number of tweets where opinions are highly unstructured and are either positive or negative, or somewhere in between of these two. For this we first pre-processed the dataset, after that extracted the adjective from the dataset that have some meaning which is called feature vector, then selected the feature vector list and thereafter applied machine learning based classification algorithms namely: Naive Bayes, Maximum entropy and SVM along with the Semantic Orientation based WordNet which extracts synonyms and similarity for the content feature. Finally we measured the performance of classifier in terms of recall, precision and accuracy.

Graph based Representation and Analysis of Text Document: A Survey of Techniques

Abstract: A common and standard approach to model text document is bag-of-words. This model is suitable for capturing word frequency, however structural and semantic information is ignored. Graph representation is mathematical constructs and can model relationship and structural information effectively. A text can appropriately represented as Graph using vertex as feature term and edge relation can be significant relation between the feature terms. Text representation using Graph model provides computations related to various operations like term weight, ranking which is helpful in many applications in information retrieval. This paper presents a systematic survey of existing work on Graph based representation of text and also focused on Graph based analysis of text document for different operations in information retrieval. In this process taxonomy of Graph based representation and analysis of text document is derived and result of different methods of Graph based text representation and analysis are discussed. The survey results shows that Graph based representation is appropriate way of representing text document and improved result of analysis over traditional model for different text applications.

Investigating neural architectures for short answer scoring

Abstract: Neural approaches to automated essay scoring have recently shown state-of-the-art performance The automated essay scoring task typically involves a broad notion of writing quality that encompasses content, grammar, organization, and conventions This differs from the short answer content scoring task, which focuses on content accuracy The inputs to neural essay scoring models – ngrams and embeddings – are arguably well-suited to evaluate content in short answer scoring tasks We investigate how several basic neural approaches similar to those used for automated essay scoring perform on short answer scoring We show that neural architectures can outperform a strong non-neural baseline, but performance and optimal parameter settings vary across the more diverse types of prompts typical of short answer scoring