Gaetano Rossiello

SABRE: A Sentiment Aspect-Based Retrieval Engine

The retrieval of pertaining information during the decision-making process requires more than the traditional concept of relevance to be fulfilled. This task asks for opinionated sources of information able to influence the user’s point of view about an entity or target. We propose SABRE, a Sentiment Aspect-Based Retrieval Engine, able to tackle this process through the retrieval of opinions about an entity at two different levels of granularity that we called aspect and sub-aspect. Such fine-grained opinion retrieval enables both an aspect-based sentiment classification of text fragments, and an aspect-based filtering during the navigational exploration of the retrieved documents. A preliminary evaluation on a manually created dataset shows the ability of the proposed method at better identify \(\langle \textit{aspect}, \textit{sub}\)-\(\textit{aspect}\rangle \) with respect to a term frequency baseline.

Centroid-based Text Summarization through Compositionality of Word Embeddings.

The textual similarity is a crucial aspect for many extractive text summarization methods. A bag-of-words representation does not allow to grasp the semantic relationships between concepts when comparing strongly related sentences with no words in common. To overcome this issue, in this paper we propose a centroidbased method for text summarization that exploits the compositional capabilities of word embeddings. The evaluations on multi-document and multilingual datasets prove the effectiveness of the continuous vector representation of words compared to the bag-of-words model. Despite its simplicity, our method achieves good performance even in comparison to more complex deep learning models. Our method is unsupervised and it can be adopted in other summarization tasks.

Learning to Rank Entity Relatedness Through Embedding-Based Features

This paper describes the effect of introducing embedding-based features in a learning to rank approach to entity relatedness. We define several features that exploit word- and link-embedding approaches by relying on both links and the content that appear in Wikipedia articles. These features are combined with other state-of-the-art relatedness measures by using a learning to rank framework. In the evaluation, we report the performance of each feature individually. Moreover, we investigate the contribution of each feature to the ranking function by analysing the output of a feature selection algorithm. The results of this analysis prove that features based on word and link embeddings are able to increase the performance of the learning to rank algorithm.

Learning Inclination to Empathy from Social Media Footprints

In recent years we are witnessing a growing spread of social media footprints, as the consequence of the wide use of applications such as Facebook, Twitter or LinkedIn, which allow people to share content that might provide information about personal preferences and aptitudes. Among the traits that can be inferred, empathy is the ability to feel and share another persons emotions and we consider it as a relevant aspect for the profiling and recommendation tasks. We propose a method that predicts its level for the user by exploiting her social media data and using linear regression algorithms. The results show which are the most relevant correlations among the different groups of users features and the empathy level predicted.

User's Social Media Profile as Predictor of Empathy

The use of social media, like Facebook, Twitter and LinkedIn, is nowadays very common and quite for sure each one of us has at least a digital profile on them. The information left of these platforms such as likes, posts, tweets and photos are very informative and can be used for deducting our preferences, tendencies and behaviors. The analysis of the social media footprints has become a relevant research topic in the last decade and many works have demonstrated how to extract some traits of the users affective sphere. In this paper, we focus on the prediction of empathic tendencies of a subject as an index of the influence of emotions during decisional processes. This value can be included in the user profile and can be relevant in some scenarios, such as music and movie recommender systems, where the emotional component is strongly delineated. We propose an approach of empathy level prediction based on a linear regression algorithm over Facebook profiles. We use a word2vec representation of the textual contents of the users time-line posts, a LDA and SVD vector representation of the users likes and other general descriptive data. The evaluation performed has demonstrated the validity of the approach for predicting the empathy tendency and the results have showed some relevant correlations with some specific groups of users descriptive features.

SEPIR: a semantic and personalised information retrieval tool for the public administration based on distributional semantics

This paper introduces a semantic and personalised information retrieval (SEPIR) tool for the public administration of Apulia Region. SEPIR, through semantic search and visualisation tools, enables the analysis of a large amount of unstructured data and the intelligent access to information. At the core of these functionalities is an NLP pipeline responsible for the WordSpace building and the key-phrase extraction. The WordSpace is the key component of the semantic search and personalisation algorithm. Moreover, key-phrases enrich the document representation of the retrieval system and are on the basis of the bubble charts, which provide a quick overview of the main concepts involved in a document collection. We show some of the key features of SEPIR in a use case where the personalisation technique re-ranks the set of relevant documents on the basis of the users past queries and the visualisation tools provide the users with useful information about the analysed collection.