Greece

Brief Presentation of the problem dealt within eTracer. How we formed the knowledge and managed it along with relationships among concepts and how we applied spatio-temporal ruled-based reasoning on top. The presentation also involves examples of implicit relationships constructs, validations examples via SHACL, system-wise evaluation, a simulation example and concludes with future work and references.

AIAI 2020

Knowledge-base Management and Reasoning on Cultural and Natural Touristic Routes

etracer

knowledge representation

reasoning

semantics

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community."<br>

*Message from the General Chair, Dirk Hovy*





<br>

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

technical paper

AIAI 2020 (16th International Conference on Artificial Intelligence Applications and Innovations) should be held in Halkidiki, Greece. Due to current Covid-19 situation the conference will be held virtually. Underline will host a repository of video talks and preserve them for the future. Videos will be released on Underline one day after the conference.

Modelling of knowledge and actions in AI has advanced over the years but it is still a challenging topic due to the infamous frame problem, the inadequate formalization and the lack of automation. Some problems in cyber security such as logical vulnerability, risk assessment, policy validation etc. still require formal approach. In this presentation we present the foundations of a new formal framework to address these challenges. Our approach is based on three-level formalisation: ontological, logical and analytical levels. Here we are presenting the first two levels which allow to model the security policies and provide a practical solution to the frame problem by efficient utilization of parameters as side effects. Key concepts are the situations, actions, events and rules. Our framework has potential use for analysis of a wide range of transactional systems within the financial, commercial and business domains and further work will include analytical level where we can perform vulnerability analysis of the model.

Ontological Foundations of Modelling Security Policies for Logical Analytics

This work proposes an efficient Content-Based (CB) product recommendation
methodology that promotes diversity. A heuristic CB approach incor- AQ1
porating feature weighting and Locality-Sensitive Hashing (LSH) is used, along
with the TF-IDF method and functionality of tuning the importance of product
features to adjust its logic to the needs of various e-commerce sites. The problem
of efficiently producing recommendations, without compromising similarity,
is addressed by approximating product similarities via the LSH technique. The
methodology is evaluated on two sets with real e-commerce data. The evaluation
of the proposed methodology shows that the produced recommendations can
help customers to continue browsing a site by providing them with the necessary
“next step”. Finally, it is demonstrated that the methodology incorporates recommendation diversity which can be adjusted by tuning the appropriate feature
weights.

Promoting Diversity in Content Based Recommendation Using Feature Weighting and LSH

Existing approaches to automated opinion classification rely either on sentiment lexicons or supervised machine learning. Deep neural networks perform this classification task particularly well by utilizing dense document representation in terms of word embeddings. However, this representation model does not consider the sentiment polarity or sentiment intensity of the words. To overcome this problem, we propose a novel model of deep neural network with word-sentiment associations. This model produces richer document representation that incorporates both word context and word sentiment. Specifically, our model utilizes pre-trained word embeddings and lexicon-based sentiment indicators to provide inputs to a deep feed-forward neural network. To verify the effectiveness of the proposed model, a benchmark dataset of Amazon reviews is used.

Opinion Mining of Consumer Reviews Using Deep Neural Networks with Word-Sentiment Associations

In recent years, many models for predicting movie ratings have been pro-posed, focusing on utilizing movie reviews combined with sentiment lexicons. In this study, we offer a different approach based on the combination of the emotionally analyzed movie script and their respective reviews. The logic behind this model is that if the emotional experience described by the reviewer match or clash with the emotions expressed in the movie script, then this correlation will be reflected in the particular rating of the movie. We collected a dataset consisting of 747 movie scripts and 78k reviews and recreated many conventional approaches for movie rating pre-diction, including Vector Semantics and Sentiment Analysis techniques ran with a variety of Machine Learning algorithms, in order to more accurately evaluate the performance of our model and validity of our hypothesis. Our results indicate that a possible combination of sentiment lexicons can achieve impressive performances, while other combinations produce a variety of outcomes.

Sentiment Analysis on Movie Scripts and Reviews

Sentiment analysis is a vigorous research area, with many application domains. In this work, aspect-based sentiment prediction is examined as a component of a larger architecture that crawls, indexes and stores documents from a wide variety of online sources, including the most popular social networks. The textual part of the collected information is processed by a hybrid bi-directional long short-term memory architecture, coupled with convolutional layers along with an attention mechanism. The extracted textual features are then combined with other characteristics, such as the number of repetitions, the type and frequency of emoji ideograms in a fully-connected, feed-forward artificial neural network that performs the final prediction task. The obtained results, especially for the negative sentiment class, which is of particular importance in certain cases, are encouraging, underlying the robustness of the proposed approach.

A deep learning approach to aspect-based sentiment prediction

Therefore, in this paper, we propose a dynamic optimization scheme for the edge computing system with multiple mobile devices (MDs), where the radio and computational resources, and ofﬂoading decisions, can be dynamically coordinated and allocated with the variation of radio resources and computation demands. Speciﬁcally, with the objective to minimize the system cost related to latency, energy consumption and weights of MDs, we propose a joint computation ofﬂoading and radio resource allocation algorithm based on Lyapunov optimization.

Dynamic Resource Allocation and Computation Offloading for Edge Computing System

This paper addresses the subject of Movie Recommendation Systems, focusing on two of the most well-known filtering techniques, Collaborative Filtering and Content-based Filtering. The first approach proposes a supervised probabilistic Bayesian model that forms recommendations based on the previous evaluations of other movies the user has watched. The second approach composes an unsupervised learning technique that forms clusters of users, using the K-Means algorithm, based on their preference of different movie genres, as it is expressed through their ratings. Both of the above approaches are compared to each other as well as to a basic method known as Weighted Sum, which makes predictions based on the cosine similarity and the euclidean distance between users and movies. In addition, Content-based Filtering is implemented through K-Means clustering techniques that focus on identifying the resemblance between movie plots. The first approach clusters movies according to the Tf/Idf weighting scheme, applying weights to the terms of movie plots. The latter identifies the likeness between movie plots, utilizing the BM25 algorithm. The efficiency of the above methods is calculated through the Accuracy metric.

Improving Movie Recommendation Systems Filtering by Exploiting User-based Reviews and Movie Synopses

The purpose of this paper is the expansion of the set-based model, namely an information retrieval model, with the use of graphs. The indexing process implements a graphical representation, while the querying and document representation are based on the classical set-based model. The root of the set-based model corresponds to the use of term sets to complete the querying process based on the terms of the query. However, in the weighting process, this paper presents a wholly different approach elaborating on algorithms that may clearly benefit the process based on the k-core decomposition of each single graph. The main focus will finally be the estimation and presentation of the most important nodes belonging to each graph. These intend to be regarded as keywords presenting the evaluation of their major influence.

A Graph-based Extension for the Set-based Model Implementing Algorithms based on Important Nodes

With the advent of social media, there is a data abundance so that analytics can be reliably designed for ultimately providing valuable information towards a given product or service. In this paper, we examine the problem of classifying hotel critiques using views expressed in users' reviews. There is a massive development of opinions and reviews on the web, which invariably include assessments of products and services, and beliefs about events and persons. In this study, we aim to face the problem of the forever increasing amount of opinionated data that is published in a variety of data sources. The intuition is the extraction of meaningful services despite the lack of sufficient existing architectures. Another important aspect that needs to be taken into consideration when dealing with brand monitoring, relates to the rapid heterogeneous data processing, which is vital to be implemented in real-time in order for the business to react in a more immediate way.

A Sentiment-based Hotel Review Summarization using Machine Learning Techniques

The data science and AI community have gathered around the world to support tackling the climate change problem in different domains. This research aims to work on air quality through emissions and pollutant concentration data along with vegetation information. Authorities, especially in urban cities like London, have been very vigilant in monitoring these different aspects of air quality and reliable sources of big data is available in this domain. This study aims to mine and collate this information spread all over the place in different formats into a usable knowledge base on which further data analysis and powerful Machine Learning approaches can be built to extract strong evidence useful in building better policies around climate change.

Downloads

Next from AIAI 2020

Ontological Foundations of Modelling Security Policies for Logical Analytics

Similar lecture

Assessing LLM Reasoning Steps via Principal Knowledge Grounding

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AIAI 2020

Ontological Foundations of Modelling Security Policies for Logical Analytics

Similar lecture

Assessing LLM Reasoning Steps via Principal Knowledge Grounding

Downloads