All trans retinoic acid has shown a remarkable effectiveness in acute promyelocytic leukemia. These results have encouraged studies of treatment with ATRA in other acute myeloid leukemia subtypes.
In ...order to evaluate toxicity and antileukemic efficacy of all ATRA in patients with relapsed or refractory non promyelocytic AML, 95 patients (median age, 58 years; range, 20 to 80 years), with unclassified AML according to the FAB classification or secondary AML at diagnosis, or refractory or relapsing AML, received induction therapy with Idarubicin, 10 mg/m(2)/day, for 3 days and cytarabine, 1000 mg/m(2)/12 h, for 6 days, alone or combined, on a randomized basis, with ATRA, 45 mg/m(2)/day, from day 1 to complete remission. Patients in CR received maintenance therapy with 6 monthly courses combining Ida, 10 mg/m(2)/day, intravenously, on day 1 with Ara-C100 mg/m(2)/day, subcutaneously, from day 1 to day 5.
Results were evaluated after one induction course. Overall 54 patients (57%, 26 with ATRA and 28 without ATRA) achieved CR including five patients treated at time of initial diagnosis, seven previously resistant, 38 in first relapse and four in further relapse. Thirty patients (31%) had resistant disease and 11 (12%) died from toxicity. Median time for neutrophil recovery to 0.5 x 10(9)/l and platelets to 20 x 10(9)/l was 31 and 21 days respectively. Severe toxicity (WHO grade >or=3) included infections (37%), diarrhea (9%), bleeding (3%), vomiting (16%), hyperbilirubinemia (5%), mucositis (6%) and hypercreatininemia (2%). No ATRA syndrome was noted in the ATRA arm. Median overall survival for the entire cohort was 6.3 months and median disease-free survival was 4.7 months. There were no statistical differences in terms of CR, DFS, and OS between the two arms.
We conclude that ATRA in combination with Ida and Ara-C can be administered safely to high-risk AML patients. However, in this setting, ATRA did not offer any advantage when compared to chemotherapy alone.
•We propose an approach for social media analysis applied to Twitter’s network.•Community detection (Tribase) and interactive visualization (NLCOMS) are provided.•Tribase is assessed on the LFR ...benchmark showing its effectiveness.•A real-world data of the ANR-Info-RSN project are considered.•The approach allows to visually reveal community structure and hidden properties.
Nowadays, social network analysis attracts more interest from the scientific community. However, it becomes trickier to analyse the generated data by the social networks due to their complexity, which hides the underlying patterns. In this work we propose an approach for social media analysis, especially for Twitter’s network. Our approach relies on two complementary steps: (i) a community identification based on a new community detection algorithm called Tribase, and (ii) an interactive community visualization, which provides gradual knowledge acquisition using our visualization tool, called NLCOMS. In order to assess the proposed approach, we have tested it on real-world data of the ANR Info-RSN project. This project is related to information propagation and community detection in Twitter’s network, more precisely on a collection of tweets dealing with media articles. The results show that our approach allows us to visually reveal the community structure and the related characteristics.
Improving Sentiment Analysis in Twitter Using Sentiment Specific Word Embeddings Othman, Rania; Abdelsadek, Youcef; Chelghoum, Kamel ...
2019 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS),
2019-Sept., Letnik:
2
Conference Proceeding
Most existing continuous word representation learning algorithms usually only capture the syntactic information in the texts while ignoring the sentiment relations between words. These represenations ...are not sufficiently effective for sentiment analysis as, in many cases, words with similar syntactic context, having neighboring word vectors can bear opposite sentiment polarity. In this paper, we present a weighted average word embeddings method which incorporates sentiment information in the continuous representation of words based on an adapted version of the delta TFIDF measure. Majority voting was then applied to determine the final polarity involving three machine learning classifiers notably, Support Vector Machine, Maximum Entropy and Naïve Bayes. Our experiments show promising results and a significant improvement over unweighted embeddings as well as traditional Term Frequency-Inverse Document Frequency (TFIDF).
Understanding the information behind social relationships represented by a network is very challenging, especially, when the social interactions change over time inducing updates on the network ...topology. In this context, this paper proposes an approach for analysing dynamic social networks, more precisely for Twitter's network. Our approach relies on two complementary steps: (i) an online community identification based on a dynamic community detection algorithm called Dyci. The main idea of Dyci is to track whether a connected component of the weighted graph becomes weak over time, in order to merge it with the "dominant" neighbour community. Additionally, (ii) a community visualization is provided by our visualization tool called NLCOMS, which combines between two methods of dynamic network visualization. In order to assess the efficiency and the applicability of the proposed approach, we consider real-world data of the ANR-Info-RSN project, which deals with community analysis in Twitter.
Nowadays, the interest given by the scientific community to the investigation of the data generated by social networks is increasing as much as the exponential increasing of social network data. The ...data structure complexity is one among the snags, which slowdown their understanding. On the other hand, community detection in social networks helps the analyzers to reveal the structure and the underlying semantic within communities. In this paper we propose an interactive visualization approach relying on our application NLCOMS, which uses synchronous and related views for graph and community visualization. Additionally, we present our algorithm for community detection in networks. A computation study is conducted on instances generated with the LFR 9-10 benchmark. Finally, in order to assess our approach on real-world data, we consider the data of the ANR-Info-RSN project. The latter addresses community detection in Twitter.