A divide-and-conquer method classifying sentence types before sentiment analysis.Classifying sentence types by the number of opinion targets a sentence contain.A data-driven approach automatically extract features from input sentences. Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

https://cyberleninka.org/article/n/1446987.pdf

Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN

Method to predict sentiment in informal texts using unsupervised dependency parsing.Algorithm based on sentiment propagation using linguistic content without training.Method to create lexicon using polarity expansion algorithm for specific domains.Our method compares favorably well with other unsupervised and supervised methods. In recent years, the explosive growth of online media, such as blogs and social networking sites, has enabled individuals and organizations to write about their personal experiences and express opinions. Classifying these documents using a polarity metric is an arduous task. We propose a novel approach to predicting sentiment in online textual messages such as tweets and reviews, based on an unsupervised dependency parsing-based text classification method that leverages a variety of natural language processing techniques and sentiment features primarily derived from sentiment lexicons. These lexicons were created by means of a semiautomatic polarity expansion algorithm in order to improve accuracy in specific application domains. The results obtained for the Cornell Movie Review, Obama-McCain Debate and SemEval-2015 datasets confirm the competitive performance and the robustness of the system.

Unsupervised method for sentiment analysis in online texts

This paper describes the STAC resource, a corpus of multi-party chats annotated for discourse structure in the style of SDRT (Asher and Lascarides, 2003; Lascarides and Asher, 2009). The main goal of the STAC project is to study the discourse structure of multi-party dialogues in order to understand the linguistic strategies adopted by interlocutors to achieve their conversational goals, especially when these goals are opposed. The STAC corpus is not only a rich source of data on strategic conversation, but also the first corpus that we are aware of that provides full discourse structures for multi-party dialogues. It has other remarkable features that make it an interesting resource for other topics: interleaved threads, creative language, and interactions between linguistic and extra-linguistic contexts.

https://hal.archives-ouvertes.fr/hal-02124399/document

Discourse Structure and Dialogue Acts in Multiparty Dialogue: the STAC Corpus

With respect to discourse organization, the most basic way of signaling the speaker’s or writer’s intentions is to use explicit lexical markers: so-called discourse markers or discourse connectives. While a lexicon of discourse connectives associated with the relations they express can be very useful for researchers, especially in Natural Language Processing, few projects aim at collecting them exhaustively, and only in a small number of languages. We present LEXCONN, a French lexicon of 328 discourse connectives, collected with their syntactic categories and the discourse relations they convey, and the methodology followed to build this resource. The lexicon has been constructed manually, applying systematic connective and relation identification criteria, using the FRANTEXT corpus as empirical support. Each connective has been associated to a relation within the framework of Segmented Discourse Representation Theory. We make a case for a few refinements in the theory, based on cases where no existing relation seemed to match a connective’s usage.

/pdf/lexconn-a-french-lexicon-of-discourse-connectives-3c6v604mv4.pdf

LEXCONN: A French Lexicon of Discourse Connectives

This paper introduces the motivation for and design of the Collaborative InterLingual Index (CILI). It is designed to make possible coordination between multiple loosely coupled wordnet projects. The structure of the CILI is based on the Interlingual index first proposed in the EuroWordNet project with several pragmatic extensions: an explicit open license, definitions in English and links to wordnets in the Global Wordnet Grid.

CILI: the Collaborative Interlingual Index.

Le projet ANNODIS vise la construction d'un corpus de textes annotes au niveau discursif ainsi que le developpement d'outils pour l'annotation et l'exploitation de corpus. Les annotations adoptent deux points de vue complementaires : une perspective ascendante part d'unites de discours minimales pour construire des structures complexes via un jeu de relations de discours ; une perspective descendante aborde le texte dans son entier et se base sur des indices pre-identifies pour detecter des structures discursives de haut niveau. La construction du corpus est associee a la creation de deux interfaces : la premiere assiste l'annotation manuelle des relations et structures discursives en permettant une visualisation du marquage issu des pretraitements ; une seconde sera destinee a l'exploitation des annotations. Nous presentons les modeles et protocoles d'annotation elabores pour mettre en œuvre, au travers de l'interface dediee, la campagne d'annotation.

/pdf/annodis-une-approche-outillee-de-l-annotation-de-structures-w3944jtfdr.pdf

ANNODIS : une approche outillée de l'annotation de structures discursives

In this paper, we propose to build a temporal ontology, which may contribute to the success of time-related applications. Temporal classifiers are learned from a set of time-sensitive synsets and then applied to the whole WordNet to give rise to TempoWordNet. So, each synset is augmented with its intrinsic temporal value. To evaluate TempoWordNet, we use a semantic vector space representation for sentence temporal classification, which shows that improvements may be achieved with the time-augmented knowledge base against a bag-of-ngrams representation.

https://hal.archives-ouvertes.fr/hal-01074964/document

TempoWordNet for sentence time tagging

This paper presents an ongoing work addressing the problem of opinion analysis. It takes part into a collaborative project with industrial partners, aiming at providing a professional with a help for strategic and technical intelligence. Thus, we focus on local semantic analysis rather than text or sentence classification. The purpose of our task-oriented approach is to characterize the properties of opinion statements in an applicative corpus. Inspired by linguistic models, the method we propose is a compositional one, consisting in detecting and analyzing valence shifters such as negation which contribute to the interpretation of the polarity and the intensity of opinion expressions. We describe our model and its first implementation before discussing the results of a proof-of-concept experiment focusing on adjectival expressions.

/pdf/opinion-analysis-the-effect-of-negation-on-polarity-and-3ozl0oqlbj.pdf

Opinion analysis: the effect of negation on polarity and intensity

Cet article presente la participation de l'equipe du GREYC a DEFT'07, en detaillant les differentes approches mises en place ainsi que les resultats obtenus. Plusieurs techniques ont ete mises en œuvre, notamment une approche a base de n-grammes, et une chaine de traitement linguistique de production d'indices. L'approche de type n-grammes a beneficie de traitements linguistiques complementaires tels que la lemmatisation et la synonymie, et constitue a elle seule un classifieur autonome. La chaine de traitements alimente quant a elle un classifieur supervise en lui fournissant des indices s'appuyant en particulier sur un lexique. Enfin, un autre classifieur a pour vocation de conjuguer les resultats obtenus par les deux traitements precedents.
 
Consulter la presentation en PDF sur : <a href=" https://deft.limsi.fr/2007/presentations/deft07_greyc-crisco.pdf"
 target="_blank"> https://deft.limsi.fr/2007/presentations/deft07_greyc-crisco.pdf . 
Consulter le document sur : <a href="https://deft.limsi.fr/actes/2007/pdf/8_vernier.pdf"
 target="_blank">https://deft.limsi.fr/actes/2007/pdf/8_vernier.pdf .

/pdf/classification-de-textes-d-opinions-une-approche-mixte-n-4brh569skb.pdf

Classification de textes d'opinions : une approche mixte n-grammes et sémantique

In this paper, we propose to build temporal ontologies from WordNet. The underlying idea is that each synset is augmented with its temporal connotation. For that purpose, temporal classifiers are iteratively learned from an initial set of time-sensitive synsets and different propagation strategies to give rise to different TempoWordNets.

/pdf/propagation-strategies-for-building-temporal-ontologies-1b5zvjegmw.pdf

Stéphane Ferrari

Papers

ANNODIS : une approche outillée de l'annotation de structures discursives

TempoWordNet for sentence time tagging

Opinion analysis: the effect of negation on polarity and intensity

Classification de textes d'opinions : une approche mixte n-grammes et sémantique

Propagation Strategies for Building Temporal Ontologies