A rule-based approach to implicit emotion detection in text

Most research in the area of emotion detection in written text focused on detecting explicit expressions of emotions in text. In this paper, we present a rule-based pipeline approach for detecting implicit emotions in written text without emotion-bearing words based on the OCC Model. We have evaluated our approach on three different datasets with five emotion categories. Our results show that the proposed approach outperforms the lexicon matching method consistently across all the three datasets by a large margin of 17–30% in F-measure and gives competitive performance compared to a supervised classifier. In particular, when dealing with formal text which follows grammatical rules strictly, our approach gives an average F-measure of 82.7% on “Happy”, “Angry-Disgust” and “Sad”, even outperforming the supervised baseline by nearly 17% in F-measure. Our preliminary results show the feasibility of the approach for the task of implicit emotion detection in written text.

Dysregulation of placental cystathionine-β-synthase promotes fetal growth restriction

Fetal growth restriction (FGR) is characterized by the birth weight and body mass below the tenth percentile for gestational age. FGR is a major cause of perinatal morbidity and mortality and babies born with FGR are prone to develop cardiovascular diseases later in life. The underlying pathology of FGR is inadequate placental transfer of nutrients from mother to fetus, which can be caused by placental insufficiency. Hydrogen sulfide (H2S), a gaseous messenger is produced endogenously by cystathionine-lyase (Cth), cystathionine-β-synthase (CBS) and 3-mercaptopyruvate sulfurtransferase (3-MST), which are present in human placenta. Recently, we demonstrated that the dysregulation of H2S/Cth pathway is associated with preeclampsia and blockade of CSE activity induces preeclampsia-like condition in pregnant mice. We hypothesized that defect in H2S pathways promote FGR and H2S donor restores fetal growth in mice where CBS or CSE activity has been compromised. Western blotting and qPCR revealed that placental CBS expressions were significantly reduced in women with FGR. ELISA analysis showed reduced placental growth factor production (PlGF) from first trimester (8–12 weeks gestation) human placental explants following inhibition of CBS activity by aminooxyacetic acid (AOA). Administration of AOA to pregnant mice had no effects on blood pressure, but caused fetal growth restriction. This was associated with reduced PlGF production. Histological analysis revealed a reduction in the placental junction zone, within which trophoblast giant cells and glycogen cells were less prominent in CBS inhibitor treated mice. These results imply that placental CBS is required for placental development and that dysregulation of CBS activity may contribute to the pathogenesis of FGR but not preeclampsia.

Dysregulation of placental cystathionine-β-synthase impact on fetal growth restriction

INTRODUCTION: Fetal growth restriction (FGR), which causes perinatal morbidity and mortality, is characterized by birth weight and body mass being below 10th percentile for gestational age. FGR babies are prone to develop cardiovascular diseases later in life. Inadequate placental transfer of nutrients from mother to fetus due to placental insufficiency is considered the underlying cause of FGR. Recently, we demonstrated that blockade of cystathionine-γ-lyase (CSE) activity induces preeclampsia-like condition in pregnant mice. We hypothesized that defect in cystathionine-β-synthase (CBS) / H2S pathway may promote FGR. METHODS: Placental CBS expressions were determined in women with FGR (n=9) and normal controls (n=14) by Western blotting and real-time qPCR. ELISA was used to determine angiogenic factors levels in plasma and first-trimester (8–12 weeks gestation) human placental explants. Time pregnant mice were treated with CBS inhibitor, aminooxyacetic acid (AOA). Mean arterial blood pressure (MBP), histological assessments of placenta and embryos were performed. RESULTS: Placental CBS expressions were significantly reduced in women with FGR. Inhibition of CBS activity by AOA reduced PlGF production from first-trimester human placental explants, Administration of AOA to pregnant mice had no effects on blood pressure, but caused fetal growth restriction, which was associated with reduced placental PlGF production. Histological analysis revealed a reduction in the placental junction zone, within which trophoblast giant cells and glycogen cells were less prominent in CBS inhibitor-treated animals. Furthermore, H2S donor GYY4137 treatment restored fetal growth in pregnant mice exposed to high level of sFlt-1. CONCLUSIONS: These results imply that placental CBS is required for placental development and that dysregulation of CBS activity may contribute to the pathogenesis of FGR but not preeclampsia opening up the therapeutic potentials of H2S therapy in this condition.