Online conversations can sometimes take a turn for the worse, either due to systematic cultural differences, accidental misunderstandings, or mere malice. Automatically forecasting derailment in public online conversations provides an opportunity to
take early action to moderate it. Previous work in this space is limited, and we extend it in several ways. We apply a pretrained language encoder to the task, which outperforms earlier approaches. We further experiment with shifting the training paradigm for the task from a static to a dynamic one to increase the forecast horizon. This approach shows mixed results: in a high-quality data setting, a longer average forecast horizon can be achieved at the cost of a small drop in F1; in a low-quality data setting, however, dynamic training propagates the noise and is highly detrimental to performance.
A reliable and continuous supply of electrical energy is necessary for the functioning
of today’s complex society. Because of the increasing consumption and the extension of
existing electrical transmission networks and these power systems are oper
ated closer and
closer to their limits accordingly the possibilities of overloading, equipment failures and
blackout are also increasing, furthermore, we have an additional obstacle which is that
electrical energy cannot be stored efficiently, so, electrical energy should be generated only
when it's needed.
Due to the fact that world is facing a lack of oil reserves and the difficulties related to
have alternative sources to generate electrical power, then, electrical load forecasting is
considered as a crucial factor in electrical power system either from economical or
technical point of view on both planning and operating levels.
This research introduces a short term electrical load forecasting system by using
artificial neural networks with a simulation in Matlab environment in addition to an
interface for the system and all that is depending on previous load data and weather
parameters in Tartous province.
Given a heterogeneous social network, can we forecast its future? Can we predict who will start using a given hashtag on twitter? Can we leverage side information, such as who retweets or follows whom, to improve our membership forecasts? We present
TENSORCAST, a novel method that forecasts time-evolving networks more accurately than the current state of the art methods by incorporating multiple data sources in coupled tensors. TENSORCAST is (a) scalable, being linearithmic on the number of connections; (b) effective, achieving over 20% improved precision on top-1000 forecasts of community members; (c) general, being applicable to data sources with a different structure. We run our method on multiple real-world networks, including DBLP and a Twitter temporal network with over 310 million nonzeros, where we predict the evolution of the activity of the use of political hashtags.
حظيت نمذجة وتوقع السلاسل الزمنية بأهمية كبيرة في العديد من المجالات التطبيقية كالتنبؤ بالطقس وأسعار العملات ومعدلات استهلاك الوقود والكهرباء، إن توقع السلاسل الزمنية من شأنه أن يزود المنظمات والشركات بالمعلومات الضرورية لاتخاذ القرارات الهامة، وبسبب
أهمية هذا المجال من الناحية التطبيقية فإن الكثير من الأعمال البحثية التي جرت ضمنه خلال السنوات الماضية، إضافةً إلى العدد الكبير من النماذج والخوارزميات التي تم اقتراحها في أدب البحث العلمي والتي كان هدفها تحسين كل من الدقة والكفاءة في نمذجة وتوقع السلاسل الزمنية.
We performed in this research forecast in the direction of the index
numbers for consumer prices for ( food- clothes and shoes –
education -health- transportation communications - housing water,
electricity, gas and other fuel oils), by using Mark
ov chains in
estimating with dependence on monthly data were taken from the
central bureau of statistics in Syria during the period (1/1/2010 ,
31/12/2011) , So results were analyzed by calculating the vector of
states probabilities in the moment 0 t and using it with matrix of
transition probabilities states transition probability for forecasting in the
vector of states probabilities on the long and short range for knowing
the direction at which the index numbers may behave in the future.
The most important results of the study were instability of the beam of
the transition probabilities (high low stability) during the prediction
period, as well as for the matrix of transition probabilities.
In this research, We present a scientific advanced developed
study and keeping up with new studies and technologies of very
short-term electrical load forecasting and applying this study for
electrical load forecasting of basic Syrian electrical p
ower system
by studying this prediction for next four hours according to the
criterion applied in the Syrian Electricity Ministry with ten minutes
intervals ,we call it "Instant electrical load forecasting".
This study includes the possibility of using Artificial neural
networks (ANNs) with back-propagation algorithm in a short-term
prediction of water level in Qattinah Lake. The data used are the
water level data in the lake and rainfall data for the period from
1/5/2007 to 28/2/2005. 2009).
The general index of the financial market of the important
economic indicators in any country is being reflects the
economic situation and economic activity in the country, so
attention must be appropriate methods for predicting the
performance o
f this indicator in the future and look at the
factors that affect in it .
This study aimed to the conclusion based, follow Box-Jenkins
methodology for building predictive models ARMA (p, q) and
check models" residuals, and predict the performance of the
general index of Damascus Securities Exchange DWX, as
well as the volume of trading in this market, and studying the
impact of the relationship between them .
In this paper, we presented a scientific methodicalness in
very short term load forecasting depends on back propagation
artificial neural networks, and we relied upon real data of Syrian
electrical power system.