Users often write reviews on different themes involving linguistic structures with complex sentiments. The sentiment polarity of a word can be different across themes. Moreover, contextual valence shifters may change sentiment polarity depending on the contexts that they appear in. Both challenges cannot be modeled effectively and explicitly in traditional sentiment analysis. Studying both phenomena requires multi-theme sentiment analysis at the word level, which is very interesting but significantly more challenging than overall polarity classification. To simultaneously resolve the multi-theme and sentiment shifting problems, we propose a data-driven framework to enable both capabilities: (1) polarity predictions of the same word in reviews of different themes, and (2) discovery and quantification of contextual valence shifters. The framework formulates multi-theme sentiment by factorizing the review sentiments with theme/word embeddings and then derives the shifter effect learning problem as a logistic regression. The improvement of sentiment polarity classification accuracy demonstrates not only the importance of multi-theme and sentiment shifting, but also effectiveness of our framework. Human evaluations and case studies further show the success of multi-theme word sentiment predictions and automatic effect quantification of contextual valence shifters.

Enterprise customers increasingly require greater flexibility in the way they access and process their Big Data while at the same time they continue to request advanced analytics and access to diverse data sources. Yet customers also still require the robustness of enterprise class analytics for their mission-critical data. In this paper, we present our initial efforts toward a solution that satisfies the above requirements by integrating the HPE Vertica enterprise database with Apache Spark's open source big data computation engine. In particular, it enables fast, reliable transferring of data between Vertica and Spark; and deploying Machine Learning models created by Spark into Vertica for predictive analytics on Vertica data. This integration provides a fabric on which our customers get the best of both worlds: it extends Vertica's extensive SQL analytics capabilities with Spark's machine learning library (MLlib), giving Vertica users access to a wide range of ML functions; it also enables customers to leverage Spark as an advanced ETL engine for all data that require the guarantees offered by Vertica.

Graph analytics is becoming increasingly popular, with a number of new applications and systems developed in the past few years. In this paper, we study Vertica relational database as a platform for graph analytics. We show that vertex-centric graph analysis can be translated to SQL queries, typically involving table scans and joins, and that modern column-oriented databases are very well suited to running such queries. Furthermore, we show how developers can trade memory footprint for significantly reduced I/O costs in Vertica. We present an experimental evaluation of the Vertica relational database system on a variety of graph analytics, including iterative analysis, a combination of graph and relational analyses, and more complex 1-hop neighborhood graph analytics, showing that it is competitive to two popular vertex-centric graph analytics systems, namely Giraph and GraphLab.

The analysis of social sentiment expressed on the Web is becoming increasingly relevant to a variety of applications, and it is important to understand the underlying mechanisms which drive the evolution of sentiments in one way or another, in order to be able to predict these changes in the future. In this paper, we study the dynamics of news events and their relation to changes of sentiment expressed on relevant topics. We propose a novel framework, which models the behavior of news and social media in response to events as a convolution between event's importance and media response function, specific to media and event type. This framework is suitable for detecting time and duration of events, as well as their impact and dynamics, from time series of publication volume. These data can greatly enhance events analysis; for instance, they can help distinguish important events from unimportant, or predict sentiment and stock market shifts. As an example of such application, we extracted news events for a variety of topics and then correlated this data with the corresponding sentiment time series, revealing the connection between sentiment shifts and event dynamics.

Topic models have been widely used to discover latent topics in text documents. However, they may produce topics that are not interpretable for an application. Researchers have proposed to incorporate prior domain knowledge into topic models to help produce coherent topics. The knowledge used in existing models is typically domain dependent and assumed to be correct. However, one key weakness of this knowledge-based approach is that it requires the user to know the domain very well and to be able to provide knowledge suitable for the domain, which is not always the case because in most real-life applications, the user wants to find what they do not know. In this paper, we propose a framework to leverage the general knowledge in topic models. Such knowledge is domain independent. Specifically, we use one form of general knowledge, i.e., lexical semantic relations of words such as synonyms, antonyms and adjective attributes, to help produce more coherent topics. However, there is a major obstacle, i.e., a word can have multiple meanings/senses and each meaning often has a different set of synonyms and antonyms. Not every meaning is suitable or correct for a domain. Wrong knowledge can result in poor quality topics. To deal with wrong knowledge, we propose a new model, called GK-LDA, which is able to effectively exploit the knowledge of lexical relations in dictionaries. To the best of our knowledge, GK-LDA is the first such model that can incorporate the domain independent knowledge. Our experiments using online product reviews show that GK-LDA performs significantly better than existing state-of-the-art models.

In this paper, we propose a novel opinion summarization problem called compact explanatory opinion summarization (CEOS) which aims to extract within-sentence explanatory text segments from input opinionated texts to help users better understand the detailed reasons of sentiments. We propose and study general methods for identifying candidate boundaries and scoring the explanatoriness of text segments using Hidden Markov Models. We create new data sets and use a new evaluation measure to evaluate CEOS. Experimental results show that the proposed methods are effective for generating an explanatory opinion summary, outperforming a standard text summarization method.

Many applications require analyzing textual topics in conjunction with external time series variables such as stock prices. We develop a novel general text mining framework for discovering such causal topics from text. Our framework naturally combines any given probabilistic topic model with time-series causal analysis to discover topics that are both coherent semantically and correlated with time series data. We iteratively refine topics, increasing the correlation of discovered topics with the time series. Time series data provides feedback at each iteration by imposing prior distributions on parameters. Experimental results show that the proposed framework is effective.

Aspect extraction is one of the key tasks in sentiment analysis.In recent years, statistical models have been used for the task.However, such models without any domain knowledge often produce aspects that are not interpretable in applications.To tackle the issue, some knowledge-based topic models have been proposed, which allow the user to input some prior domain knowledge to generate coherent aspects.However, existing knowledge-based topic models have several major shortcomings, e.g., little work has been done to incorporate the cannot-link type of knowledge or to automatically adjust the number of topics based on domain knowledge.This paper proposes a more advanced topic model, called MC-LDA (LDA with m-set and c-set), to address these problems, which is based on an Extended generalized Pólya urn (E-GPU) model (which is also proposed in this paper).Experiments on real-life product reviews from a variety of domains show that MC-LDA outperforms the existing state-of-the-art models markedly.

Aeolus is a prototype implementation of a topology optimizer on top of the distributed streaming system Storm. Aeolus extends Storm with a batching layer which can increase the topology's throughput by more than one order of magnitude. Furthermore, Aeolus implements an optimization algorithm that computes the optimal batch size and degree of parallelism for each node in the topology automatically. Even if Aeolus is built on top of Storm, the developed concepts are not limited to Storm and can be applied to any distributed intra-node-parallel streaming system. We propose to demo Aeolus using an interactive Web UI. One part of the Web UI is a topology builder allowing the user to interact with the system. Topologies can be created from scratch and their structure and/or parameters can be modified. Furthermore, the user is able to observe the impact of the changes on the optimization decisions and runtime behavior. Additionally, the Web UI gives a deep insight in the optimization process by visualizing it. The user can interactively step through the optimization process while the UI shows the optimizer's state, computations, and decisions. The Web UI is also able to monitor the execution of a non-optimized and optimized topology simultaneously showing the advantage of using Aeolus.

Opinionated social media such as product reviews are now widely used by individuals and organizations for their decision making. However, due to the reason of profit or fame, people try to game the system by opinion spamming (e.g., writing fake reviews) to promote or to demote some target products. In recent years, fake review detection has attracted significant attention from both the business and research communities. However, due to the difficulty of human labeling needed for supervised learning and evaluation, the problem remains to be highly challenging. This work proposes a novel angle to the problem by modeling spamicity as latent. An unsupervised model, called Author Spamicity Model (ASM), is proposed. It works in the Bayesian setting, which facilitates modeling spamicity of authors as latent and allows us to exploit various observed behavioral footprints of reviewers. The intuition is that opinion spammers have different behavioral distributions than non-spammers. This creates a distributional divergence between the latent population distributions of two clusters: spammers and non-spammers. Model inference results in learning the population distributions of the two clusters. Several extensions of ASM are also considered leveraging from different priors. Experiments on a real-life Amazon review dataset demonstrate the effectiveness of the proposed models which significantly outperform the state-of-the-art competitors.

We introduce a novel sentence ranking problem called explanatory sentence extraction (ESE) which aims to rank sentences in opinionated text based on their usefulness for helping users understand the detailed reasons of sentiments (i.e., "explanatoriness"). We propose and study several general methods for scoring the explanatoriness of a sentence. We create new data sets and propose a new measure for evaluation. Experiment results show that the proposed methods are effective, outperforming a state of the art sentence ranking method for standard text summarization.

Since stream analytics is treated as a kind of cloud service, there exists a pressing need for its reliability and fault-tolerance. In a streaming process, the parallel and distributed tasks are chained in a graph-structure with each task transforming a stream to a new stream, the transaction property guarantees the streaming data, called tuples, to be processed in the order of their generation in every dataflow path, with each tuple processed once and only once. The failure recovery of a task allows the previously produced results to be corrected for eventual consistency, which is different from the instant consistency of global state enforced by the failure recovery of general distributed systems, and therefore presents new technical challenges. Transactional stream processing typically requires every task to checkpoint its execution state, and when it is restored from a failure, to have the last state recovered from the checkpoint and missing tuple re-acquired and processed. Currently there exist two kind approaches: one treats the whole process as a single transaction, and therefore suffers from the loss of intermediate results during failures, the other relies on the receipt of acknowledgement (ACK) to decide whether moving forward to emit the next resulting tuple or resending the current one after timeout, on the per-tuple basis, thus incurs extremely high latency penalty. In contradistinction to the above, we propose the backtrack mechanism for failure recovery, which allows a task to process tuples continuously without waiting for ACKs and without resending tuples in the failure-free case, but to request (ASK) the source tasks to resend the missing tuples only when it is restored from a failure which is a rare case thus has limited impact on the overall performance. We have implemented the proposed mechanisms on Fontainebleau, the distributed stream analytics infrastructure we developed on top of Storm. As a principle, we ensure all the transactional properties to be system supported and transparent to users. Our experience shows that the ASK-based recovery mechanism significantly outperforms the ACK-based one.

Topic modeling is popular for text mining tasks. Recently, topic modeling has been combined with time lines when textual data is related to external non-textual time series data such as stock prices. However, no previous work has used the external non-textual time series data in the process of topic modeling. In this paper, we describe a novel text mining system, Integrative Causal Topic Miner (InCaToMi) that integrates textual and non-textual time series data. InCaToMi automatically finds causal relationships and topics using text data and external non-textual time series data using Granger Testing. Moreover, InCaToMi considers the non-textual time series data in the topic modeling process, using the time series data to iteratively improve modeling results through interactions between it and the textual data at both topic and word levels.

The rapid proliferation of online forums has made it possible for people to share their intentions, wishes and experiences by posting comments with the aim of getting advice from other members of the forum. Extracting intentions from these comments provides valuable insight for companies who can exploit it to get a competitive edge. However, given the very large amount of this kind of online comments, manually extracting intentions is impractical, time consuming and expensive. Companies need tools that analyze the text to extract intentions and details about them. In this paper we propose to demo one such tool called Intention Insider which has been developed at HP Labs in close collaboration with business units and a few selected customers. The tool can ingest content from online forums or from uploaded files and quickly sift through very large amounts of comments to extract intention information. This information is loaded into a data warehouse to be correlated with other structured data and queried to produce interactive reports and dynamic visualizations that facilitate its exploration at detailed and aggregate levels.

Next generation business intelligence involves data flows that span different execution engines, contain complex functionality like data/text analytics, machine learning operations, and need to be optimized against various objectives. Creating correct analytic data flows in such an environment is a challenging task and is both labor-intensive and time-consuming. Optimizing these flows is currently an ad-hoc process where the result is largely dependent on the abilities and experience of the flow designer. Our previous work addressed analytic flow optimization for multiple objectives over a single execution engine. This paper focuses on optimizing flows for a single objective, namely performance, over multiple execution engines. We consider flows that span a DBMS, a Map-Reduce engine, and an orchestration engine (e.g., an ETL tool or scripting language). This configuration is emerging as a common paradigm used to combine analysis of unstructured data with analysis of structured data (e.g., NoSQL plus SQL). We present flow transformations that model data shipping, function shipping, and operation decomposition and we describe how flow graphs are generated for multiple engines. Performance results for various configurations demonstrate the benefit of optimization.

The rise of Web 2.0 with its increasingly popular social sites like Twitter, Facebook, blogs and review sites has motivated people to express their opinions publicly and more frequently than ever before. This has fueled the emerging field known as sentiment analysis whose goal is to translate the vagaries of human emotion into hard data. LCI is a social channel analysis platform that taps into what is being said to understand the sentiment with the particular ability of doing so in near real-time. LCI integrates novel algorithms for sentiment analysis and a configurable dashboard with different kinds of charts including dynamic ones that change as new data is ingested. LCI has been researched and prototyped at HP Labs in close interaction with the Business Intelligence Solutions (BIS) Division and a few customers. This paper presents an overview of the architecture and some of its key components and algorithms, focusing in particular on how LCI deals with Twitter and illustrating its capabilities with selected use cases.

The explosion of Web opinion data has made essential the need for automatic tools to analyze and understand people's sentiments toward different topics. In most sentiment analysis applications, the sentiment lexicon plays a central role. However, it is well known that there is no universally optimal sentiment lexicon since the polarity of words is sensitive to the topic domain. Even worse, in the same domain the same word may indicate different polarities with respect to different aspects. For example, in a laptop review, "large" is negative for the battery aspect while being positive for the screen aspect. In this paper, we focus on the problem of learning a sentiment lexicon that is not only domain specific but also dependent on the aspect in context given an unlabeled opinionated text collection. We propose a novel optimization framework that provides a unified and principled way to combine different sources of information for learning such a context-dependent sentiment lexicon. Experiments on two data sets (hotel reviews and customer feedback surveys on printers) show that our approach can not only identify new sentiment words specific to the given domain but also determine the different polarities of a word depending on the aspect in context. In further quantitative evaluation, our method is proved to be effective in constructing a high quality lexicon by comparing with a human annotated gold standard. In addition, using the learned context-dependent sentiment lexicon improved the accuracy in an aspect-level sentiment classification task.

Improving the performance and functionality of database system optimizers requires experimentation on real customer data. Often these data are of sensitive nature and the only way to keep them is by applying a non-reversible transformation to obfuscate them. However, in order that the database optimizer generates exactly the same query plans as for the sensitive data, the transformation has to preserve the order and some important properties of the data distribution. Unfortunately, existing data obfuscation techniques do not preserve all of these properties and therefore are not applicable in this context. In this paper we present a Desensitizer tool that we have developed for optimizer performance experiments of HP's Neoview high availability data warehousing product. The tool is based on novel numeric and string desensitization algorithms which are agnostic to the database system. We explain the core concepts behind the algorithms, how they preserve the required data properties and important implementation considerations that were made. We present the architecture of the Desensitizer tool and results of the extensive validation that we conducted.

Extract-Transform-Load (ETL) processes play an important role in data warehousing. Typically, design work on ETL has focused on performance as the sole metric to make sure that the ETL process finishes within an allocated time window. However, other quality metrics are also important and need to be considered during ETL design. In this paper, we address ETL design for performance plus fault-tolerance and freshness. There are many reasons why an ETL process can fail and a good design needs to guarantee that it can be recovered within the ETL time window. How to make ETL robust to failures is not trivial. There are different strategies that can be used and they each have different costs and benefits. In addition, other metrics can affect the choice of a strategy; e.g., higher freshness reduces the time window for recovery. The design space is too large for informal, ad-hoc approaches. In this paper, we describe our QoX optimizer that considers multiple design strategies and finds an ETL design that satisfies multiple objectives. In particular, we define the optimizer search space, cost functions, and search algorithms. Also, we illustrate its use through several experiments and we show that it produces designs that are very near optimal.

Emerging business intelligence (BI) applications aim to provide situational awareness, i.e., information about real-world events that might affect the business operations of an enterprise. For instance, an enterprise might want to know whether customers are posting positive or negative comments about a new product it has just introduced; or whether some natural disaster affects its contracted suppliers. It is difficult to develop such applications today because they require extracting and correlating facts from multiple streaming and stored data sources, typically including unstructured data, which is not well supported by BI platforms today. In this paper, we describe SIE-OBI, a system that we are developing to enable the development and execution of such applications. We describe the novel features of this system, including a declarative interface for rapidly developing such applications, and a platform for optimizing and executing the applications. We illustrate its applicability through two use cases.

Business processes drive the operations of an enterprise. In the past, the focus was primarily on business process design, modeling, and automation. Recently, enterprises have realized that they can benefit tremendously from analyzing the behavior of their business processes with the objective of optimizing or improving them. In our research, we address the problem of warehousing business process execution data so that we can analyze their behavior using the analytic and reporting tools that are available in data warehouse environments. We build upon our previous work that described the design and implementation of a generic process data warehouse for use with any business processes. In this paper, we show how to automate the population of the generic process warehouse by tracking business events from an application environment. Typically, the source data consists of event streams that

Business Intelligence (BI) refers to technologies, tools, and practices for collecting, integrating, analyzing, and presenting large volumes of information to enable better decision making. Today's BI architecture typically consists of a data warehouse (or one or more data marts), which consolidates data from several operational databases, and serves a variety of front-end querying, reporting, and analytic tools. The back-end of the architecture is a data integration pipeline for populating the data warehouse by extracting data from distributed and usually heterogeneous operational sources; cleansing, integrating and transforming the data; and loading it into the data warehouse. Since BI systems have been used primarily for off-line, strategic decision making, the traditional data integration pipeline is a oneway, batch process, usually implemented by extract-transform-load (ETL) tools. The design and implementation of the ETL pipeline is largely a labor-intensive activity, and typically consumes a large fraction of the effort in data warehousing projects. Increasingly, as enterprises become more automated, data-driven, and real-time, the BI architecture is evolving to support operational decision making. This imposes additional requirements and tradeoffs, resulting in even more complexity in the design of data integration flows. These include reducing the latency so that near real-time data can be delivered to the data warehouse, extracting information from a wider variety of data sources, extending the rigidly serial ETL pipeline to more general data flows, and considering alternative physical implementations. We describe the requirements for data integration flows in this next generation of operational BI system, the limitations of current technologies, the research challenges in meeting these requirements, and a framework for addressing these challenges. The goal is to facilitate the design and implementation of optimal flows to meet business requirements.

QuickStart is a tool to automate the physical design of data warehouses for HP's Neoview system. It has been researched and prototyped at HP Labs with close interaction from Neoview design experts. It embodies heuristics and best practices of the experts to search for candidate physical features and uses cost calculations to recommend the features that result in good designs. It has some unique characteristics that differentiate it from other physical design advisors. In particular, it is the only advisor that is client-based, does not require a DBMS server installation and can work off a laptop by simply connecting to the customers' flat files. Another unique characteristic of QuickStart is that it provides the rationale for its recommendations.

As business intelligence becomes increasingly essential for organizations and as it evolves from strategic to operational, the complexity of Extract-Transform-Load (ETL) processes grows. In consequence, ETL engagements have become very time consuming, labor intensive, and costly. At the same time, additional requirements besides functionality and performance need to be considered in the design of ETL processes. In particular, the design quality needs to be determined by an intricate combination of different metrics like reliability, maintenance, scalability, and others. Unfortunately, there are no methodologies, modeling languages or tools to support ETL design in a systematic, formal way for achieving these quality requirements. The current practice handles them with ad-hoc approaches only based on designers' experience. This results in either poor designs that do not meet the quality objectives or costly engagements that require several iterations to meet them. A fundamental shift that uses automation in the ETL design task is the only way to reduce the cost of these engagements while obtaining optimal designs. Towards this goal, we present a novel approach to ETL design that incorporates a suite of quality metrics, termed QoX, at all stages of the design process. We discuss the challenges and tradeoffs among QoX metrics and illustrate their impact on alternative designs.

The conceptual design of the Extract -- Transform -- Load (ETL) processes is a crucial, burdensome, and challenging procedure that takes places at the early phases of a Data Warehouse project. Several models have been proposed for the conceptual design and representation of ETL processes, but all share two inconveniences: they require intensive human effort from the designers to create them, as well as technical knowledge from the business people to understand them. In a previous work, we have relaxed the former difficulty by working on the automation of the conceptual design leveraging Semantic Web technology. In this paper, we built upon our previous results and we tackle the second issue by investigating the application of natural language generation techniques to the ETL environment. In particular, we provide a method for the representation of a conceptual ETL design as a narrative, which is the most natural means of communication and does not require knowledge of any specific model. We discuss how linguistic techniques can be used for the establishment of a common application vocabulary. Finally, we present a flexible and customizable template-based mechanism for generating natural language representations for the ETL process requirements and operations.

Presents the introductory welcome message from the conference proceedings.

This paper discusses process analysis issues, especially in the context of outsourced processes. In particular, we describe a process warehousing solution developed at HP along with the challenges we had to face and the lessons we learned in implementing and deploying it.

As IT systems become more and more complex and as business operations become increasingly automated, there is a growing need from business managers to have better control on business operations and on how these are aligned with business goals. This paper describes iBOM, a platform for business operation management developed by HP that allows users to i) analyze operations from a business perspective and manage them based on business goals; ii) define business metrics, perform intelligent analysis on them to understand causes of undesired metric values, and predict future values; iii) optimize operations to improve business metrics. A key aspect is that all this functionality is readily available almost at the click of the mouse. The description of the work proceeds from some specific requirements to the solution developed to address them. We also show that the platform is indeed general, as demonstrated by subsequent deployment domains other than finance.

In this paper we propose a novel approach and a platform for dynamic service selection in composite Web services. The problem we try to solve is that of selecting, for each composite service execution and for each step in the execution, the service that maximizes the probability of reaching a user-defined goal. We first underline the limitations of a priori approaches based on having each service provider declare non-functional parameters and on trying to select services based on some utility functions over these parameters. Then, we propose an approach that overcomes these limitations by tackling the problem a posteriori: we analyze past executions of the composite service and build, using data mining techniques, a set of context-sensitive service selection models to be applied at each stage in the composite service execution. We show the architecture of a prototype that implements this approach and we discuss its benefits over the a priori approach.

The process of integrating the schemas of several databases into an integrated schema is not easy, due to semantic heterogeneities. We present a method/sup 1/ to detect class similarities by following a strategy and applying comparison criteria, that exploits the semantically rich structures of the schemas (previously enriched), along both the generalization/specialization and the aggregation dimensions. Relaxations may be applied to conform a pair of classes, resulting in penalizations in the computation of the degree of similarity. Our approach needs less comparisons than methods based on attribute comparison.>