Aspect-based sentiment analysis is an important tool to understand user opinions in a fine-grained manner. Although extensively studied, developing such a tool for a specific domain remains an expensive process. Most existing methods either rely on massive labeled data for training or external language resource and tools which are not necessarily available or accurate. We propose to study the aspect-based sentiment analysis with only a small set of aspect and sentiment seed words as guidance on a target corpus. We first expand the aspect and sentiment lexicons from the given seed words by features created by frequent pattern mining. Then, we develop a generative model to characterize the aspect and sentiment mentions based on their word embedding, and infer the sentiment polarity for sentiment words accordingly. The effectiveness of our method is verified by experiments on two real world data sets.

Fuzzy systems are known to be excellent for reasoning where information is uncertain, incomplete, imprecise, and/or vague. Over the past several years, work has been done to prototype an automated value of information (VoI) decision support tool for military intelligence analysts. The system was constructed using the type-1 fuzzy sets. Recently, the use of type-2 fuzzy sets has been proffered as an alternative to account for the differing opinions expressed by the experts during the knowledge elicitation process. Compounding this challenge for the military is the fact that military science is as much an art as it is a science. The work described in this paper focuses on the investigation with respect to transitioning to type-2 fuzzy sets.

Data cube is a cornerstone architecture in multidimensional analysis of structured datasets. It is highly desirable to conduct multidimensional analysis on text corpora with cube structures for various text-intensive applications in healthcare, business intelligence, and social media analysis. However, one bottleneck to constructing text cube is to automatically put millions of documents into the right cube cells so that quality multidimensional analysis can be conducted afterwards-it is too expensive to allocate documents manually or rely on massively labeled data. We propose Doc2Cube, a method that constructs a text cube from a given text corpus in an unsupervised way. Initially, only the label names (e.g., USA, China) of each dimension (e.g., location) are provided instead of any labeled data. Doc2Cube leverages label names as weak supervision signals and iteratively performs joint embedding of labels, terms, and documents to uncover their semantic similarities. To generate joint embeddings that are discriminative for cube construction, Doc2Cube learns dimension-tailored document representations by selectively focusing on terms that are highly label-indicative in each dimension. Furthermore, Doc2Cube alleviates label sparsity by propagating the information from label names to other terms and enriching the labeled term set. Our experiments on real data demonstrate the superiority of Doc2Cube over existing methods.

Pattern-based methods have been successful in information extraction and NLP research. Previous approaches learn the quality of a textual pattern as relatedness to a certain task based on statistics of its individual content (e.g., length, frequency) and hundreds of carefully-annotated labels. However, patterns of good content-quality may generate heavily conflicting information due to the big gap between relatedness and correctness. Evaluating the correctness of information is critical in (entity, attribute, value)-tuple extraction. In this work, we propose a novel method, called TruePIE, that finds reliable patterns which can extract not only related but also correct information. TruePIE adopts the self-training framework and repeats the training-predicting-extracting process to gradually discover more and more reliable patterns. To better represent the textual patterns, pattern embeddings are formulated so that patterns with similar semantic meanings are embedded closely to each other. The embeddings jointly consider the local pattern information and the distributional information of the extractions. To conquer the challenge of lacking supervision on patterns' reliability, TruePIE can automatically generate high quality training patterns based on a couple of seed patterns by applying the arity-constraints to distinguish highly reliable patterns (i.e., positive patterns) and highly unreliable patterns (i.e., negative patterns). Experiments on a huge news dataset (over 25GB) demonstrate that the proposed TruePIE significantly outperforms baseline methods on each of the three tasks: reliable tuple extraction, reliable pattern extraction, and negative pattern extraction.

With the urbanization process worldwide, modeling the dynamics of people's activities in urban environments has become a crucial socioeconomic task. We present Urbanity, a novel system that leverages geo-tagged social media streams for modeling urban dynamics. Urbanity automatically discovers the spatial and temporal hotspots where people's activities concentrate; and captures the cross-modal correlations among location, time, and text by jointly mapping different units into the same latent space. With Urbanity, the end users are able to use flexible query schemes to retrieve different resources (e.g., POIs, hotspots, hours, activities) that meet their needs. Furthermore, Urbanity can handle continuous streams to update the learned model, thus revealing up-to-date patterns of urban activities.

The objective of this paper is to motivate human computation research, leveraged with the advantages of fuzzy-based systems, within the military situational awareness domain. The goal is to stimulate the use of fuzzy logic's ability for providing more intuitive ways to model complex systems as the basis for research aimed toward facilitating human computation in the context of improving military situational awareness.

Current military decision making requires the ability to amalgamate a volume, velocity, variety and veracity of information not seen in most other domains. Confounding the calculation for the value of this information is the realization that seldom does the information agree. Appreciative of these challenges, strides have been made to successfully capture and codify how analysts perceive the value of information (VoI) given its source, content, and latency. Capitalizing on this past success, this paper broadens the scope of VoI research and examines two important and interrelated efforts. Presented first is a novel approach that extends the original VoI calculation from a single element of information to an amalgamation of multiple elements of information that either complement or contradict the original premise. Presented second is a `human-inside-the-loop' concept designed to assist in scaling future autonomous Vol methodologies - effectively interleaving human and machine computation.

Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the parsing results lose rich context around entities in the patterns, and the process is costly for a corpus of large scale. In this study, we propose a novel typed textual pattern structure, called meta pattern, which is extended to a frequent, informative, and precise subsequence pattern in certain context. We propose an efficient framework, called MetaPAD, which discovers meta patterns from massive corpora with three techniques: (1) it develops a context-aware segmentation method to carefully determine the boundaries of patterns with a learnt pattern quality assessment function, which avoids costly dependency parsing and generates high-quality patterns; (2) it identifies and groups synonymous meta patterns from multiple facets---their types, contexts, and extractions; and (3) it examines type distributions of entities in the instances extracted by each group of patterns, and looks for appropriate type levels to make discovered patterns precise. Experiments demonstrate that our proposed framework discovers high-quality typed textual patterns efficiently from different genres of massive corpora and facilitates information extraction.

Detecting local events (e.g., protest, disaster) at their onsets is an important task for a wide spectrum of applications, ranging from disaster control to crime monitoring and place recommendation. Recent years have witnessed growing interest in leveraging geo-tagged tweet streams for online local event detection. Nevertheless, the accuracies of existing methods still remain unsatisfactory for building reliable local event detection systems. We propose TrioVecEvent, a method that leverages multimodal embeddings to achieve accurate online local event detection. The effectiveness of TrioVecEvent is underpinned by its two-step detection scheme. First, it ensures a high coverage of the underlying local events by dividing the tweets in the query window into coherent geo-topic clusters. To generate quality geo-topic clusters, we capture short-text semantics by learning multimodal embeddings of the location, time, and text, and then perform online clustering with a novel Bayesian mixture model. Second, TrioVecEvent considers the geo-topic clusters as candidate events and extracts a set of features for classifying the candidates. Leveraging the multimodal embeddings as background knowledge, we introduce discriminative features that can well characterize local events, which enables pinpointing true local events from the candidate pool with a small amount of training data. We have used crowdsourcing to evaluate TrioVecEvent, and found that it improves the performance of the state-of-the-art method by a large margin.

Spatiotemporalactivity modeling is an important task for applications like tour recommendation and place search. The recently developed geographical topic models have demonstrated compelling results in using geo-tagged social media (GTSM) for spatiotemporal activity modeling. Nevertheless, they all operate in batch and cannot dynamically accommodate the latest information in the GTSM stream to reveal up-to-date spatiotemporal activities. We propose ReAct, a method that processes continuous GTSM streams and obtains recency-aware spatiotemporal activity models on the fly. Distinguished from existing topic-based methods, ReAct embeds all the regions, hours, and keywords into the same latent space to capture their correlations. To generate high-quality embeddings, it adopts a novel semi-supervised multimodal embedding paradigm that leverages the activity category information to guide the embedding process. Furthermore, as new records arrive continuously, it employs strategies to effectively incorporate the new information while preserving the knowledge encoded in previous embeddings. Our experiments on the geo-tagged tweet streams in two major cities have shown that ReAct significantly outperforms existing methods for location and activity retrieval tasks.

With the ever-increasing urbanization process, systematically modeling people's activities in the urban space is being recognized as a crucial socioeconomic task. This task was nearly impossible years ago due to the lack of reliable data sources, yet the emergence of geo-tagged social media (GTSM) data sheds new light on it. Recently, there have been fruitful studies on discovering geographical topics from GTSM data. However, their high computational costs and strong distributional assumptions about the latent topics hinder them from fully unleashing the power of GTSM.

Understanding human mobility is of great importance to various applications, such as urban planning, traffic scheduling, and location prediction. While there has been fruitful research on modeling human mobility using tracking data (e.g., GPS traces), the recent growth of geo-tagged social media (GeoSM) brings new opportunities to this task because of its sheer size and multi-dimensional nature. Nevertheless, how to obtain quality mobility models from the highly sparse and complex GeoSM data remains a challenge that cannot be readily addressed by existing techniques. We propose GMove, a group-level mobility modeling method using GeoSM data. Our insight is that the GeoSM data usually contains multiple user groups, where the users within the same group share significant movement regularity. Meanwhile, user grouping and mobility modeling are two intertwined tasks: (1) better user grouping offers better within-group data consistency and thus leads to more reliable mobility models; and (2) better mobility models serve as useful guidance that helps infer the group a user belongs to. GMove thus alternates between user grouping and mobility modeling, and generates an ensemble of Hidden Markov Models (HMMs) to characterize group-level movement regularity. Furthermore, to reduce text sparsity of GeoSM data, GMove also features a text augmenter. The augmenter computes keyword correlations by examining their spatiotemporal distributions. With such correlations as auxiliary knowledge, it performs sampling-based augmentation to alleviate text sparsity and produce high-quality HMMs.

In today's military environment vast amounts of disparate information are available. To aid situational awareness it is vital to have some way to judge information importance. Recent research has developed a fuzzy-based system to assign a Value of Information (VoI) determination for individual pieces of information. This paper presents an investigation of the effect of integrating subsequent complementary and/or contradictory information into the VoI process. Specifically, the idea of using complementary and/or contradictory new information to impact the previously used fuzzy membership values for the information content characteristic applied in the VoI calculations is shown to be a particularly suitable approach.

A major event often has repercussions on both news media and microblogging sites such as Twitter. Reports from mainstream news agencies and discussions from Twitter complement each other to form a complete picture. An event can have multiple aspects (sub-events) describing it from multiple angles, each of which attracts opinions/comments posted on Twitter. Mining such reflections is interesting to both policy makers and ordinary people seeking information. In this paper, we propose a unified framework to mine multi-aspect reflections of news events in Twitter. We propose a novel and efficient dynamic hierarchical entity-aware event discovery model to learn news events and their multiple aspects. The aspects of an event are linked to their reflections in Twitter by a bootstrapped dataless classification scheme, which elegantly handles the challenges of selecting informative tweets under overwhelming noise and bridging the vocabularies of news and tweets. In addition, we demonstrate that our framework naturally generates an informative presentation of each event with entity graphs, time spans, news summaries and tweet highlights to facilitate user digestion.

Today's military operations require information from an unprecedented number of sources resulting in an overwhelming volume of collected data. A primary challenge for military commanders and their staff is separating the important information from the routine. Currently, the Value of Information (VOI) assigned a piece of information is a multiple step process requiring intelligence collectors and analysts to judge its value within a host of differing operational situations. The cognitive processes behind these conclusions resist codification with exact precision suggesting that new methodologies are required to deal with this significant issue. This paper presents an approach for calculating the VOI in complex military environments using a fuzzy associative memory model as an effective framework for contextually tuning the VOI based on the information's content, source reliability and latency.

Multicontext team decision making under time stress is an extremely challenging issue faced by various real-world application domains. In this paper, we employ an experience-based cognitive agent architecture (called R-CAST) to address the informational challenges associated with military command and control (C2) decision-making teams, the performance of which can be significantly affected by dynamic context switching and tasking complexities. Using context switching frequency and task complexity as two factors, we conducted an experiment to evaluate whether the use of R-CAST agents as teammates and decision aids can benefit C2decision-making teams. Members from a U.S. Army Reserve Officer Training Corps organization were randomly recruited as human participants. They were grouped into ten human-human teams, each composed of two participants, and ten human-agent teams, each composed of one participant and two R-CAST agents, as teammates and decision aids. The statistical inference of experimental results indicates that R-CAST agents can significantly improve the performance of C2teams in multicontext decision making under varying time-stressed situations.

Summary form only given. To achieve superior video compression performance it is generally necessary to base the encoding decisions on a local scale, instead of the traditional frame-by-frame approach. Partitioning schemes for optimal frame subdivision have been proposed. Unfortunately, a full local approach that leads to inhomogeneous partitioning of the frame encounters the serious problem of dealing with an increase of side information, particularly in the area of very low bit-rate compression where a relatively large overhead can possibly erode the benefits of the local analysis. Our approach adopts a moderate position, which can still retain some of the advantages of variable block size while keeping the overhead to a bare minimum. The idea is to subdivide a frame in a fixed number of square panels that we call "megablocks." All decisions relative to intra (I) or inter (P) coding are made at the megablock level. These decisions pertain to motion block size and degree of error quantization in the P-mode as well as vector and scalar quantization of subbands in the I-mode. The key to the improved performance of the megablock partitioning scheme is the joint cost minimization of motion field and quantized error information. In very low bit rate video coding, the cost of transmitting motion vectors consumes a significant fraction of the total bit budget. The megablock structure permits the use of variable size motion blocks without incurring the cost associated with motion segmentation or a full quadtree approach.

TED (Turbine Engine Diagnostics) is a diagnostic expert system to aid an M1 Abrams tank mechanic in finding and fixing problems in an AGT-1500 turbine engine. TED was designed to provide apprentice mechanics with the ability to diagnose and repair a turbine engine like an expert mechanic. This paper discusses the reasoning method used in TED, called the Procedural Reasoning System (PRS), as well as various design considerations throughout the life of the project. The expert system was designed and built by the US Army Research Laboratory and the US Army Ordnance Center. TED has been fielded to both the active Army and the National Guard.

No abstract available.