1,721,134 research outputs found
Towards Emotion-aware Recommender Systems: an Affective Coherence Model based on Emotion-driven Behaviors
Get PDFDecision making is the cognitive process of identifying and choosing alternatives based on preferences, beliefs, and degree of importance given by the decision maker to objects or actions. For instance, choosing which movie to watch is a simple, small-sized decision-making process. Recommender systems help people to make this kind of choices, usually by computing a short list of suggestions that reduces the space of possible options. These systems are strongly based on the knowledge of user preferences but, in order to fully support people, they should be grounded on a holistic view of the user behavior, that includes also how emotions, mood, and personality traits influence her choosing patterns.
In this work, we investigate how to include emotional aspects in the recommendation process. We suggest that the affective state of the user, defined by a set of emotions (e.g., joy, surprise), constitutes part of choosing situation that should be taken into account when modeling user preferences.
The main contribution of the paper is a general emotion-aware computational model based on affective user profiles in which each preference, such as a 5-star rating on a movie, is associated with the affective state felt by the user at the time when that preference was collected.
The model estimates whether an unseen item is suitable for the current affective state of the user, by computing an affective coherence score that takes into account both the affective user profile and not-affective item features. The approach has been implemented into an Emotion-aware Music Recommender System, whose effectiveness has been assessed by performing in-vitro experiments on two benchmark datasets. The main outcome is that our system showed improved accuracy of recommendations compared to baselines which include no affective information in the recommendation model
SWAP at SemEval-2019 Task 3: Emotion detection in conversations through Tweets, CNN and LSTM deep neural networks
No full textEmotion detection from user-generated contents is growing in importance in the area of natural language processing. The approach we proposed for the EmoContext task is based on the combination of a CNN and an LSTM using a concatenation of word embeddings. A stack of convolutional neural networks (CNN) is used for capturing the hierarchical hidden relations among embedding features. Meanwhile, a long short-term memory network (LSTM) is used for capturing information shared among words of the sentence. Each conversation has been formalized as a list of word embeddings, in particular during experimental runs pre-trained Glove and Google word embeddings have been evaluated. Surface lexical features have been also considered, but they have been demonstrated to be not usefully for the classification in this specific task. The final system configuration achieved a micro F1 score of 0.7089. The python code of the system is fully available at https://github.com/marcopoli/EmoContext201
Context-aware graph-based recommendations exploiting Personalized PageRank
Get PDFIn this article we present a context-aware recommendation method that exploits graph-based data models and Personalized PageRank to provide users with recommendations.
In particular, our approach extends the basic graph-based representation that relies on users and items nodes by introducing a third class of nodes, that is to say, context nodes, whose goal is to model the different contextual situations in which an item can be consumed. Given such a data model, we used Personalized PageRank to identify the most suitable recommendations for each user: in a nutshell, our model is based on the intuition that context nodes shall be used to influence random walks, in order to assist the algorithm in identifying the items that are relevant in a particular contextual setting.
In the experimental evaluation we investigated the effectiveness of the approach on three different datasets. The results showed that our context-aware graph-based approach overcame the baselines in most of the experimental settings and obtained the best overall results in cold-start situations, thus confirming the validity of the methodology
An emotion-driven approach for aspect-based opinion mining
No full textThe remarkable ability to understand the opinion of a user about a specific topic of discussion allows intelligent systems to provide more specific and personalized suggestions especially when no other information is available. The strategies for opinion mining, also known as sentiment analysis, are in last years topic of in-depth studies. In this work, we present an approach of text mining for detecting the topic of discussion for textual contents and the emotion that the writer feels while writing it. Conversely to the classic strategies of sentiment analysis, we enrich the standard polarity prediction task with more fine-grained information about user’s emotion. By using this information, the final behavior of the personalized system could be designed by taking into account the view about the topic of the specific user. For performing this task, we adopted a hybrid approach which uses both lexicons and semantic representation of sentences for the operation of aspect classification. Training data for the aspects detection module have been extracted from already categorized last year world news. The emotional labeling approach is, instead, based on the posts left by users on Facebook, which have been annotated using the emoticon encountered. The evaluation has been conducted on a dataset of tweets opportunely collected using hash-tags which refer both to the topic of discussion and the emotional opinion
Word Embedding techniques for Content-based Recommender Systems: An empirical evaluation
No full textThis work presents an empirical comparison among three widespread word embedding techniques as Latent Semantic Indexing, Random Indexing and the more recent Word2Vec. Specifically, we employed these techniques to learn a low-dimensional vector space word representation and we exploited it to represent both items and user profiles in a content-based recommendation scenario. The performance of the techniques has been evaluated against two state-of-the-art datasets, and experimental results provided good in-sights which pave the way to several future directions
Social Tags and Emotions as main Features for the Next Song To Play in Automatic Playlist Continuation
No full textAlBERTo: Modeling Italian Social Media Language with BERT
Get PDFNatural Language Processing tasks recently achieved considerable interest and progresses following the development of numerous innovative artificial intelligence models released in recent years. The increase in available computing power has made possible the application of machine learning approaches on a considerable amount of textual data, demonstrating how they can obtain very encouraging results in challenging NLP tasks by generalizing the properties of natural language directly from the data. Models such as ELMo, GPT/GPT-2, BERT, ERNIE, and RoBERTa have proved to be extremely useful in NLP tasks such as entailment, sentiment analysis, and question answering. The availability of these resources mainly in the English language motivated us towards the realization of AlBERTo, a natural language model based on BERT and trained on the Italian language. We decided to train AlBERTo from scratch on social network language, Twitter in particular, because many of the classic tasks of content analysis are oriented to data extracted from the digital sphere of users. The model was distributed to the community through a repository on GitHub and the Transformers library (Wolf et al. 2019) released by the development group huggingface.co. We have evaluated the validity of the model on the classification tasks of sentiment polarity, irony, subjectivity, and hate speech. The specifications of the model, the code developed for training and fine-tuning, and the instructions for using it in a research project are freely available
- …
