Andreas Kanavos

Identifying Personality-Based Communities in Social Networks

In this paper we present a novel algorithm for forming communities in a graph representing social relations as they emerge from the use of services like Twitter. The main idea centers in the careful use of features to characterize the members in the community, and in the hypothesis that well formed communities are those that designate diversity in the features of the participating members.

Modeling ReTweet Diffusion Using Emotional Content

In this paper we present a prediction model for forecasting the depth and the width of ReTweeting using data mining techniques. The proposed model utilizes the analyzers of tweet emotional content based on Ekman emotional model, as well as the behavior of users in Twitter. In following, our model predicts the category of ReTweeting diffusion. The model was trained and validated with real data crawled by Twitter. The aim of this model is the estimation of spreading of a new post which could be retweeted by the users in a particular network. The classification model is intended as a tool for sponsors and people of marketing to specify the tweets that spread more in Twitter network.

Large Scale Implementations for Twitter Sentiment Classification

Sentiment Analysis on Twitter Data is indeed a challenging problem due to the nature, diversity and volume of the data. People tend to express their feelings freely, which makes Twitter an ideal source for accumulating a vast amount of opinions towards a wide spectrum of topics. This amount of information offers huge potential and can be harnessed to receive the sentiment tendency towards these topics. However, since no one can invest an infinite amount of time to read through these tweets, an automated decision making approach is necessary. Nevertheless, most existing solutions are limited in centralized environments only. Thus, they can only process at most a few thousand tweets. Such a sample is not representative in order to define the sentiment polarity towards a topic due to the massive number of tweets published daily. In this work, we develop two systems: the first in the MapReduce and the second in the Apache Spark framework for programming with Big Data. The algorithm exploits all hashtags and emoticons inside a tweet, as sentiment labels, and proceeds to a classification method of diverse sentiment types in a parallel and distributed manner. Moreover, the sentiment analysis tool is based on Machine Learning methodologies alongside Natural Language Processing techniques and utilizes Apache Spark’s Machine learning library, MLlib. In order to address the nature of Big Data, we introduce some pre-processing steps for achieving better results in Sentiment Analysis as well as Bloom filters to compact the storage size of intermediate data and boost the performance of our algorithm. Finally, the proposed system was trained and validated with real data crawled by Twitter, and, through an extensive experimental evaluation, we prove that our solution is efficient, robust and scalable while confirming the quality of our sentiment identification.

Evaluating Twitter Influence Ranking with System Theory

A considerable part of social network analysis literature is dedicated to determining which individuals are to be considered as influential in particular social settings. Most established algorithms, such as Freeman and KatzBonacich centrality metrics, place emphasis on various structural properties of the social graph. Although this makes centrality metrics generic enough to be applied in virtually any setting, they are oblivious to the functionality of the underlying social network. This paper examines five social influence metrics designed especially for Twitter and their implementation in a Java client retrieving network information from a Neo4j server. Additionally, a sceheme is proposed for evaluating the performance of an influence ranking based on estimating the exponent of a Zipf model fitted to the ranking score.

Tensor-based document retrieval over Neo4j with an application to PubMed mining

PubMed mining is currently at the epicenter of intense interdisciplinary research. Text mining methodologies provide a way to retrieve and analyze emotionally charged words, punctuation, and syntax. Moreover, they can analyze scientific literature and process document collections. Moving beyond traditional document-term matrix representation, an architecture for content based retrieval from PubMed is proposed whose core is a document-term-author third order tensor. This methodology has been implemented in Python over Neo4j and has been applied to a PubMed document article collection.

Extracting Knowledge from Web Search Engine Results

Nowadays, people frequently use search engines in order to find the information they need on the web. However, usually web search engines return web page references in a global ranking making it difficult to the users to browse different topics captured in the result set and thus making it difficult to find quickly the desired web pages. There is need for special computational systems, that will discover knowledge in these web search results providing the user with the possibility to browse different topics contained in a given result set. In this paper, we focus on the problem of determining different thematic groups on web search engine results that existing web search engines provide. We propose a novel system that exploits a set of reformulation strategies so as to help users gain more relevant results to their desired query. It additionally tries to discover among the result set different topic groups, according to the various meanings of the provided query. The proposed method utilizes a number of semantic annotation techniques using Knowledge Bases, like Word Net and Wikipedia, in order to perceive the different senses of each query term. Finally, the method annotates the extracted topics using information derived from the clusters and presents them to the end user.

Integrating User’s Emotional Behavior for Community Detection in Social Networks

The analysis of social networks is a very challenging research area. A fundamental aspect concerns the detection of user communities, i.e. the organization of vertices in clusters, with many edges joining vertices of the same cluster and comparatively few edges joining vertices of different clusters. Detecting communities is of great importance in sociology, biology as well as computer science where systems are often represented as graphs. In this paper we present a novel methodology for community detection based on users’ emotional behavior. The methodology analyzes user’s tweets in order to determine their emotional behavior in Ekman emotional scale. We define two different metrics to count the influence of produced communities. Moreover, the weighted version of a modularity community detection algorithm is utilized. Our results show that our proposed methodology creates influential enough communities.

On Topic Categorization of PubMed Query Results

Nowadays, people frequently use search engines in order to find the information they need on the Web. Especially Web search constitutes a basic tool used by million researchers in their everyday work. A very popular indexing engine, concerning life sciences and biomedical research is PubMed. PubMed is a free database accessing primarily the MEDLINE database of references and abstracts on life sciences and biomedical topics. The present search engines usually return search results in a global ranking making it difficult to the users to browse in different topics or subtopics that they query. Because of this mixing of results belonging to different topics, the average users spend a lot of time to find Web pages, best matching their query. In this paper, we propose a novel system to address this problem. We present and evaluate a methodology that exploits semantic text clustering techniques in order to group biomedical document collections in homogeneous topics. In order to provide more accurate clustering results, we utilize various biomedical ontologies, like MeSH and GeneOntology. Finally, we embed the proposed methodology in an online system that post-processes the PubMed online database in order to provide to users the retrieved results according to well formed topics.

Emotional community detection in social networks

Abstract It is vastly acknowledged that analyzing social networks is a very challenging research area. Take as a striking example the organization of vertices in clusters, with many edges joining vertices of the same cluster and comparatively few edges joining vertices of different clusters. This comprises a fundamental aspect, which concerns the detection of user communities. In certain fields such as sociology and computer science where interactions and associations are often represented in the form of graphs, detecting communities is of vital importance. This paper addresses the need for an efficient and innovative methodology for community detection that will also leverage users’ behavior on emotional level. Ekman emotional scale is the key point with which the methodology analyzes user’s tweets in order to determine their emotional behavior. Consequently, the derived communities are estimated with the use of three different metrics, while the weighted version of a modularity community detection algorithm is utilized. There is substantial evidence indicating that our proposed methodology creates influential enough communities.

An Apache Spark Implementation for Sentiment Analysis on Twitter Data.

Sentiment Analysis on Twitter Data is a challenging problem due to the nature, diversity and volume of the data. In this work, we implement a system on Apache Spark, an open-source framework for programming with Big Data. The sentiment analysis tool is based on Machine Learning methodologies alongside with Natural Language Processing techniques and utilizes Apache Spark’s Machine learning library, MLlib. In order to address the nature of Big Data, we introduce some pre-processing steps for achieving better results in Sentiment Analysis. The classification algorithms are used for both binary and ternary classification, and we examine the effect of the dataset size as well as the features of the input on the quality of results. Finally, the proposed system was trained and validated with real data crawled by Twitter and in following results are compared with the ones from real users.