A Novel Method for Unsupervised and Supervised Conversational Message Thread Detection

Communications in Computer and Information Science

et al. 2017

Self Cite

Conversational message thread identification regards a wide spectrum of applications, ranging from social network marketing to virus propagation, digital forensics, etc. Many different approaches have been proposed in literature for the identification of conversational threads focusing on features that are strongly dependent on the dataset. In this paper, we introduce a novel method to identify threads from any type of conversational texts overcoming the limitation of previously determining specific features for each dataset. Given a pool of messages, our method extracts and maps in a three dimensional representation the semantic content, the social interactions and the timestamp; then it clusters each message into conversational threads. We extend our previous work by introducing a deep learning approach and by performing new extensive experiments and comparisons with classical learning algorithms.

Section: Introductionmentioning

confidence: 99%

Identifying Conversational Message Threads by Integrating Classification and Data Clustering

Domeniconi

Semertzidis

Communications in Computer and Information Science

et al. 2017

Self Cite

“…(see in [46] for an extensive treatment in transfer learning). Moreover this study can be extended to cope with other emerging text classification problems where large data sets are unlabelled, such as in thread of conversational messages of social networks and discussion forums [47,48].…”

Section: Discussionmentioning

confidence: 99%

Transfer Learning in Sentiment Classification with Deep Neural Networks

Pagliarani

Communications in Computer and Information Science

Pasolini

et al. 2019

Self Cite

Cross-domain sentiment classifiers aim to predict the polarity (i.e. sentiment orientation) of target text documents, by reusing a knowledge model learnt from a different source domain. Distinct domains are typically heterogeneous in language, so that transfer learning techniques are advisable to support knowledge transfer from source to target. Deep neural networks have recently reached the state-of-the-art in many NLP tasks, including in-domain sentiment classification, but few of them involve transfer learning and cross-domain sentiment solutions. This paper moves forward the investigation started in a previous work [1], where an unsupervised deep approach for text mining, called Paragraph Vector (PV), achieved cross-domain accuracy equivalent to a method based on Markov Chain (MC), developed ad hoc for crossdomain sentiment classification. In this work, Gated Recurrent Unit (GRU) is included into the previous investigation, showing that memory units are beneficial for cross-domain when enough training data are available. Moreover, the knowledge models learnt from the source domain are tuned on small samples of target instances to foster transfer learning. PV is almost unaffected by fine-tuning, because it is already able to capture word semantics without supervision. On the other hand, fine-tuning boosts the crossdomain performance of GRU. The smaller is the training set used, the greater is the improvement of accuracy.

“…For years, researchers have tried to automate extracting valuable and structured knowledge from raw text [8][9][10][11]. This research field is named Natural Language Processing (NLP), and it had recent crucial breakthroughs, thanks to deep neural networks.…”

Section: Organization Of the Papermentioning

confidence: 99%

“…For years, researchers have developed methods and algorithms to automate the extraction of valuable and structured knowledge from raw text [ 10 , 11 , 12 , 13 ], even with computational linguistic and algebraic approaches, such as the latent semantic analysis [ 14 ]. This research field, which is named Natural Language Processing (NLP), has produced crucial breakthroughs thanks to recent deep learning advancements.…”

Section: Introductionmentioning

confidence: 99%

Efficient Self-Supervised Metric Information Retrieval: A Bibliography Based Method Applied to COVID Literature

Valgimigli

2021

Sensors

Self Cite

The literature on coronaviruses counts more than 300,000 publications. Finding relevant papers concerning arbitrary queries is essential to discovery helpful knowledge. Current best information retrieval (IR) use deep learning approaches and need supervised train sets with labeled data, namely to know a priori the queries and their corresponding relevant papers. Creating such labeled datasets is time-expensive and requires prominent experts’ efforts, resources insufficiently available under a pandemic time pressure. We present a new self-supervised solution, called SUBLIMER, that does not require labels to learn to search on corpora of scientific papers for most relevant against arbitrary queries. SUBLIMER is a novel efficient IR engine trained on the unsupervised COVID-19 Open Research Dataset (CORD19), using deep metric learning. The core point of our self-supervised approach is that it uses no labels, but exploits the bibliography citations from papers to create a latent space where their spatial proximity is a metric of semantic similarity; for this reason, it can also be applied to other domains of papers corpora. SUBLIMER, despite is self-supervised, outperforms the Precision@5 (P@5) and Bpref of the state-of-the-art competitors on CORD19, which, differently from our approach, require both labeled datasets and a number of trainable parameters that is an order of magnitude higher than our.