Michal Shmueli-Scheuer

Extracting user profiles from large scale data

In this work we present the details of a large scale user profiling framework that we developed here in IBM on top of Apache Hadoop. We address the problem of extracting and maintaining a very large number of user profiles from large scale data. We first describe an efficient user profiling framework with high user profiling quality guarantees. We then describe a scalable implementation of the proposed framework in Apache Hadoop and discuss its challenges.

Surfacing time-critical insights from social media

We propose to demonstrate an end-to-end framework for leveraging time-sensitive and critical social media information for businesses. More specifically, we focus on identifying, structuring, integrating, and exposing timely insights that are essential to marketing services and monitoring reputation over social media. Our system includes components for information extraction from text, entity resolution and integration, analytics, and a user interface.

Predicting Customer Satisfaction in Customer Support Conversations in Social Media Using Affective Features

Providing customer support through social media channels is gaining popularity. In such a context, predicting customer satisfaction in an early stage of a service conversation is important. Such an analysis can help personalize agent assignment to maximize customer satisfaction, and prioritize conversations. In this paper, we show that affective features such as customers and agents personality traits and emotion expression improve prediction of customer satisfaction when added to more typical text based features. We only utilize information extracted from the first customer conversation turn and previous customer and agent social network activity. Thus, our customer satisfaction classifier outputs its prediction in an early stage of the conversation, before any interaction has taken place between the customer and an agent. Our model was trained and tested on a Twitter conversations dataset of two customer support services, and shows an improvement of 30% in F1-score for predicting dissatisfaction.

A statistical approach to mining customers' conversational data from social media

In this paper, we present one possible way of analyzing social media conversional data in order to better understand customers. Ultimately, our goal is to analyze customer behavior as it is expressed in free-form conversations and extract from it commercially valuable information about the customer. In this study, we concentrate on using statistical techniques for analyzing this unstructured data at two levels: 1) at the level of the words used in the conversation and 2) by mapping those words to abstract concepts. The goal of such a statistical analysis is twofold. First, the statistically significant terms used by the users and the concepts associated with them provide insight on a users interests that commercial services can use, for example, in order to target advertisements. In addition, knowing the evolution of a customers interests and hobbies can be exploited commercially by retailers, media and entertainment companies, telecommunications companies, and more. In this paper, we describe a general framework for the analysis of social media data and, in turn, the application of the framework to the statistical analysis of the language of tweets.

Classifying Emotions in Customer Support Dialogues in Social Media

Providing customer support through social media channels is gaining increasing popularity. In such a context, automatic detection and analysis of the emotions expressed by customers is important, as is identification of the emotional techniques (e.g., apology, empathy, etc.) in the responses of customer service agents. Result of such an analysis can help assess the quality of such a service, help and inform agents about desirable responses, and help develop automated service agents for social media interactions. In this paper, we show that, in addition to text based turn features, dialogue features can significantly improve detection of emotions in social media customer service dialogues and help predict emotional techniques used by customer service agents.

A scalable and effective full-text search in P2P networks

We consider the problem of full-text search involving multi-term queries in a network of self-organizing, autonomous peers. Existing approaches do not scale well with respect to the number of peers, because they either require access to a large number of peers or incur a high communication cost in order to achieve good query results. In this paper, we present a novel algorithmic framework for processing multi-term queries in P2P networks that achieves high recall while using (per-query) a small number of peers and a low communication cost, thereby enabling high query throughput. Our approach is based on per-query peer-selection strategy using two-dimensional histograms of score distributions. A full utilization of the histograms incurs a high communication cost. We show how to drastically reduce this cost by employing a two-phase peer-selection algorithm. We also describe an adaptive approach to peer selection that further increases the recall. Experiments on a large real-world collection show that the recall is indeed high while the number of involved peers and the communication cost are low.

SoLoMo analytics for telco Big Data monetization

The mobile Internet brought tremendous opportunities for businesses to capitalize on the vast amount of SoLoMo (social-location-mobile) data for delivering high-quality and personalized customer services. In this paper, we describe algorithms and technologies for discovering actionable customer insights using the combined power of social network, location pattern mining, and mobile usage analysis. We illustrate our implementation using Big Data platforms including IBM InfoSphere® BigInsights, IBM InfoSphere Streams, and IBM Netezza® Data Warehouse, while addressing various Big Data-related challenges, such as context generation of unstructured data and high-performance analytics for both data at rest and data in motion. The presented system combines location, social interactions, and user behavior data to find like-minded communities. The system leverages Big Data capabilities to attempt to scale to support the subscriber base of large telecoms in an efficient manner.

Greaaaat bargains starting from just 99p!!!! :-): brand perception in the social media

In this work we discuss the challenges of utilizing social media data, and more specifically microblogs, for helping brand managers. Brand perception is one of the most important tasks of a brand manager, requiring to understand how customers perceive and select brands in specific product categories or market segments. While understanding the brand perception from conventional sources such as reviews and advertisement is well studied and established, gaining insights from social media sources is still an open challenge. In this paper, we present a high-level overview of a novel system that was developed in IBM which aims at extracting brand perception from Twitter. As a proof of concept, we present some preliminary results from the retail domain.

KMV-peer: a robust and adaptive peer-selection algorithm

The problem of fully decentralized search over many collections is considered. The objective is to approximate the results of centralized search (namely, using a central index) while controlling the communication cost and involving only a small number of collections. The proposed solution is couched in a peer-to-peer (P2P) network, but can also be applied in other setups. Peers publish per-term summaries of their collections. Specifically, for each term, the range of document scores is divided into intervals; and for each interval, a KMV (K Minimal Values) synopsis of its documents is created. A new peer-selection algorithm uses the KMV synopses and two scoring functions in order to adaptively rank the peers, according to the relevance of their documents to a given query. The proposed method achieves high-quality results while meeting the above criteria of efficiency. In particular, experiments are done on two large, real-world datasets; one is blogs and the other is web data. These experiments show that the algorithm outperforms the state-of-the-art approaches and is robust over different collections, various scoring functions and multi-term queries.

EHCTool: Managing Emotional Hotspots for Conversational Agents

Building conversational agents is becoming easier thanks to the profusion of designated platforms. Integrating emotional intelligence in such agents contributes to positive user satisfaction. Currently, this integration is implemented using calls to an emotion analysis service. In this demonstration we present EHCTool that aims to detect and notify the conversation designer about problematic conversation states where emotions are likely to be expressed by the user. Using its exploration view, the tool assists the designer to manage and define appropriate responses in these cases.