Sentiment Factors Research Articles

Impact of lexical and sentiment factors on the popularity of scientific papers.

We investigate how textual properties of scientific papers relate to the number of citations they receive. Our main finding is that correlations are nonlinear and affect differently the most cited and typical papers. For instance, we find that, in most journals, short titles correlate positively with citations only for the most cited papers, whereas for typical papers, the correlation is usually negative. Our analysis of six different factors, calculated both at the title and abstract level of 4.3 million papers in over 1500 journals, reveals the number of authors, and the length and complexity of the abstract, as having the strongest (positive) influence on the number of citations.

Market Sentiment Dynamics and Return Volatility in the Indian Equity Market

In this study, we constructed a composite index of irrational market sentiment to ascertain the impact of market sentiment upon return volatility in the Indian equity market using monthly data spanning the time period from April 2007 to January 2015 of four major indices of Bombay Stock Exchange such as : BSE Sensex, BSE 500, BSE Mid-cap, BSE Small-cap. The Sentindex significantly portrayed the fluctuations in accordance with the events that took place in the market during the period of analysis, and at the same time, its movements were found to be uncorrelated with that of economic fundamentals. Though the graphical analysis showed indications of higher fluctuations in returns in times of pessimistic sentiments and moderate and calm period of volatility regimes with moderate positive sentiment in the market, from further investigation, we observed that the effect of sentiment was significant only in case of the volatilities in medium and small cap portfolio returns. On examination of temporal dependency, based on ARDL modeling, we noticed significant long-term relationship between return volatility and irrational sentiments in case of such portfolios. An initial shock in the sentiment component was found to create varying magnitude of responses in volatility over the months and was observed to be disappearing after four to five months. These observations necessitate the incorporation of sentiment factors in the pricing models of assets as well as in risk estimation, especially in case of those stocks with the characteristics that are sensitive to market sentiment. Along with this, in order to pinpoint the causes of the persistence of sentiment effects, further investigations on : the nature and trading behavior of investors who participate in such market segments, level of trading and fund flows, sophistication of trading mechanism, and effectiveness of policy level initiatives to eliminate market inefficiency in these segments is recommended.

Single Stock Call Options as Lottery Tickets

This paper investigates whether the overpricing of out-of-the money single stock calls can be explained by Tversky and Kahneman’s (1992) cumulative prospect theory (CPT). We hypothesize that these options are overpriced because investors overweight small probability events and overpay for positively skewed securities that resemble lottery tickets. We match a set of subjective density functions derived from risk-neutral densities with the empirical probability distribution of U.S. equity returns. We find that overweighting of small probabilities embedded in the CPT explains the richness of out-of-the money single stock calls better than other utility functions. The overweighting of small probability events is less pronounced than suggested by the CPT, is strongly time-varying and most frequent in options of short maturity. We find that the fluctuations in overweighting of small probabilities are to a large degree explained by the sentiment factor of Baker and Wurgler (2007).

Detecting similar opinion holders for massive sentiment analysis

Sentiment Analysis is the study of acquisition, extraction and interpretation of human opinions, sentiments, attitudes and emotions from both structured and unstructured data sources. Also called opinion mining, the field is becoming crucial for various application areas including market researches, politics, sociology and economics. Therefore, many outstanding research efforts are performed on the fields including both theoretical and practical aspects. This paper aims to develop a supportive framework for sentiment analysis, focusing on the similarity of opinion holders in a massive dataset. We used e-commerce review dataset of Amazon spanning May 1996 – July 2014. The whole review set includes more than 140 million entries. As a preprocessing task each review is structured and expressed on a quadruple form of 4 dimensions: Target entity, opinion holder, sentiment and time. The aim of this study is to find out similar opinion holders for a given customer on a certain product in real time. We have defined a new method spanning all the opinions of an individual. The idea behind this calculation of similarity is rating of the same product with the same sentiment factor by two different opinion holders. The real-time calculation is also performed on Hadoop clusters. Performance enhancements and accuracy rates are then discussed.Keywords: sentiment analysis, opinion mining, big data analytics, Map-Reduce

An Unsupervised Cross-Lingual Topic Model Framework for Sentiment Classification

Sentiment classification aims to determine the sentiment polarity expressed in a text. In online customer reviews, the sentiment polarities of words are usually dependent on the corresponding aspects. For instance, in mobile phone reviews, we may expect the long battery time but not enjoy the long response time of the operating system. Therefore, it is necessary and appealing to consider aspects when conducting sentiment classification. Probabilistic topic models that jointly detect aspects and sentiments have gained much success recently. However, most of the existing models are designed to work well in a language with rich resources. Directly applying those models on poor-quality corpora often leads to poor results. Consequently, a potential solution is to use the cross-lingual topic model to improve the sentiment classification for a target language by leveraging data and knowledge from a source language. However, the existing cross-lingual topic models are not suitable for sentiment classification because sentiment factors are not considered therein. To solve these problems, we propose for the first time a novel cross-lingual topic model framework which can be easily combined with the state-of-the-art aspect/sentiment models. Extensive experiments in different domains and multiple languages demonstrate that our model can significantly improve the accuracy of sentiment classification in the target language.

Market Sentiment as a Factor in Asset Pricing

This paper explores whether market sentiment should be used as an additional factor in the asset-pricing model. We use a unique dataset from Investor Intelligence as a direct measure of market sentiment. We form ten portfolios based on their correlations with the new market sentiment measure. Following Fama and French (1993) we build a market sentiment factor (SENT) and add this factor to the Carhart four-factor model. We find that SENT is significant for all portfolios in the sentiment augmented four-factor model and increases explanatory power of the model measured by adjusted R2s. We also find that the addition of SENT factor reduces the explanatory power of all other risk factors in the four-factor model.

Sentiment Risk, Sentiment Timing, and Hedge Fund Returns

We examine whether exposure to sentiment risk helps explain the cross-sectional variation in hedge fund returns. We find that funds with sentiment beta in the top decile subsequently outperform those in the bottom decile by 0.67% per month on a risk-adjusted basis. Further, we show that some hedge funds have the ability to time sentiment by having high exposure to a sentiment factor when the factor premium is high, and sentiment timing also contributes to fund performance. Our results are robust to controlling for fund characteristics and other risk factors known to affect hedge fund returns and hold for alternative sentiment risk measures. Overall, these findings highlight sentiment risk as a source of limits to arbitrage faced by hedge funds.

Trieste 1954. Echi italiani della "seconda redenzione"

In October 1954 Trieste returned to Italy, after 9 years of Anglo-American military government and hard politics and diplomatic conflicts with the new Yugoslavia of Tito. The second redemption, after the one of 1918, resulted in large public demonstrations, since the city, despite its complex ethnic reality, was identified in Italy as the memory of the Great War, the nation, the fatherland, the italianita. In the context of the cold war and of the new political situation of the Italian Republic, the article analyzes the representations and the languages of the political myth of Trieste and its presence in the national public memory. The popular press, the cine-newspapers Incom, the telegrams sent to the Prime Minister allow to explore some aspects of the public and private receipt of the image of Trieste: together with the persistence of sentimental factors that feed that image, it is also possible to see the signals of crisis of the patriotic myths along the changes that Italy would have lived in the years of the great transformation.

The Butcher, Vintner, and Cidermaker: Crafting Good Food in Contemporary America

We are experiencing a contemporary “renaissance” of craft food production in America. Although recent scholarship has highlighted the marketing and consumption of artisanal foods as socially, culturally, and economically interesting, fewer scholars focus on artisanal production. Amidst the relative paucity of academic interest, anthropologist Heather Paxson has persuasively argued that American artisan cheese gains status as an object good to make in the same way that it achieves its distinction as an object good to eat. My investigations elaborate on this claim to show that the complex variables motivating artisanal cheese production extend, alongside if not neatly parallel, to other American artisan food domains as well. I argue that it is the moral component of making in which artisans simultaneously craft “good” products and themselves as “good” producers that gives meaning and value to the quotidian aspects of their daily lives. Employing an ethnographic approach that juxtaposes three diverse artisan food producers—a butcher, vintner, and cidermaker— I show that artisans are imbued with a vital sense of agency and are motivated by the belief that their labour and their lives are employed in the production of not only material objects but a better world. In better understanding the motivations of craft food production, we learn that the meaning and constitution of the “good life” can be realized in myriad ways and, more narrowly, to appreciate that sentimental factors buttress socio-economic behaviour as much as the predominant logic of neoliberalism.

A mixture language model for the classification of Chinese online reviews

In this essay, we propose an unsupervised topic and sentiment mixture model (LSS model) mainly on the basis of LDA model and combining with the sentiment factor, as an approach to sentiment classification of online reviews. There is an extra constraint that all words in a sentence are generated from one topic and one sentiment. Which means the hypothesis of the model is a word in a sentence is of one meaning only. LSS model is totally unsupervised and it needs no labelled corpora or any other sentiment seed words. Experiments show that LSS model performs better than JST model and ASUM model. The F-1 value of sentiment classification is 8% higher than ASUM model and 12.5% than JST model.

A Study on the Correlations between Investor Sentiment and Stock Index and Macro Economy Based on EEMD Method

This paper tried to utilize Ensemble Empirical Mode Decomposition (EEMD) to explore the correlations between investor sentiment and stock index and macro economy, as well as the prediction capacity of the short-term fluctuation, medium-term fluctuation and long-term trend of investor sentiment in the future stock market return. Firstly, dynamic factor model (DFM) was used to extract sentiment factors from 5 proxy variables of investor sentiment. Then, characteristics comparison and lead-lag relationship analyses were made on the short-term fluctuation, medium-term fluctuation and long-term trend of investor sentiment index, Shanghai Stock Index and macro index. Finally, whether the original signals of investor sentiment and each component can predict the size and the direction of future market returns was tested. Results indicated that high-frequency sentiment signals had a significant reverse prediction capacity on the short-term and medium-term future market returns. Moreover, low-frequency sentiment signals had a stronger prediction capacity in the direction of future market returns than original sentiment signals, high-frequency sentiment signals and residual signals.

The Profitability Premium: Macroeconomic Risks or Expectation Errors?

Macroeconomic risks only partially capture the relation between profitability and future stock returns, while an investor sentiment factor explains a substantial amount of the profitability premium. More importantly, the profitability premium concentrates in firms whose market valuations are inconsistent with their profitability and therefore more subject to ex-ante expectation errors. We provide further evidence that firms with high profitability but low market valuation have significantly higher abnormal earnings announcement returns, analyst earnings forecast errors and forecast revisions than firms with low profitability but high market valuation. Moreover, the profitability premium only exists during high sentiment periods for firms with ex-ante expectation errors. Our results suggest that mispricing due to errors in expectation plays an important role in explaining the profitability premium.

Liquidity and real estate asset pricing: a pan-European study

Purpose– Understanding the pricing of real estate equities is a central objective of real estate research. This paper aims to investigate the impact of liquidity on European real estate equity returns, after accounting for well-documented systematic risk factors.Design/methodology/approach– Based on risk factors derived from general equity data, the authors extend the Fama-French time-series regression approach by a liquidity factor, using a pan-European sample of 272 real estate equities.Findings– The empirical results indicate that liquidity is a significant pricing factor in real estate stock returns, even after controlling for market, size and book-to-market factors. In addition, the authors detect that real estate stock returns load predominantly positively on the liquidity risk factor, suggesting that real estate equities tend to behave like illiquid common equities. These findings are underpinned by a series of robustness checks. Running a comparative analysis with alternative factor models, the authors further demonstrate that the liquidity-augmented asset-pricing model is most appropriate for explaining European real estate stock returns.Research limitations/implications– The inclusion of sentiment and downside risk factors could provide further insights into real estate asset pricing in European capital markets.Originality/value– This is the first study to examine the role of liquidity as a systematic risk factor in a pan-European setting.

Effect of Sentiment on the Bangladesh Stock Market Returns

This paper looks at Bangladesh stock market completely from behavioral perspective by introducing behavioral factors in the empirical asset pricing models. Lack of data of sentiment proxies constrains authors to use only few proxies, namely, TRIN (Trading Index), trade volume (turnover), number of IPOs per month and change in four-month moving average. We have found that TRIN and moving average significantly affect the residual market returns. This paper also investigates the impact of sentiment on returns of different size portfolios. Results show that the impact of TRIN and trade volume is strong for large and medium size portfolios. However, the effect of TRIN is either low or insignificant for small size portfolio, indicating less interest of investors for neglected stocks. Granger causality tests show that there is unidirectional causality from TRIN to stock returns and strong bi-directional causal relationship between moving average change and stock returns. When conditional volatility is taken into account, effect of sentiment on returns from market and size portfolios decreases and we mostly observe significant effect of sentiment on small size portfolios. Finally, in the presence of other market-wide risk factors, sentiment factors weakly explain individual stock returns. Overall, we conclude that sentiment is a non-negligible consideration for portfolio investors in Bangladesh.

Note about the 'anxious bench'

[MWS 14.1 (2014) 97-101] ISSN 1470-8078 Note about the 'anxious bench' Mariana Magalhäes Pinto Côrtes In the section dedicated to Methodism in his The Protestant Ethic and the Spirit of Capitalism, Max Weber briefly mentions a strange and unprecedented conversion technique practised during the move ment of the 'Second Great Awakening'. This technique was called the 'anxious bench'. Weber doesn't use the original English term, probably—although there is no certainty on this point—because he only knew about the technique from the German translation of the book written by the theologian and educator John Williamson Nevin called The Anxious Bench-A Tract for the Times, published in 1843.1 1. In the famous translation of The Protestant Ethic and the Spirit of Capitalism by Talcott Parsons, the 'anxious bench' was referred to only indirectly. To quote the Par sons' translation: The attainment of repentance under certain circumstances involved an emotional struggle of such intensity as to lead to the most terrible ecstasies, which in America often took place in a public meeting. This formed the basis of a belief in the undeserved possession of divine grace and at the same time of an immediate consciousness of justifica tion and forgiveness (Weber 1930:140). 'In a public meeting' stands in for the 'Angstbank'. The German reads: Ein unter Umständen bis zu den fürchterlichsten Ekstasen gesteiger ter Busskampf, in Amerika mit Vorliebe auf der "Angstbank" vollzo gen, führte zum Glauben an Gottes unverdiente Gnade und zugleich damit unmittelbar zum Be wusstein der Rechtfertigung und Versöh nung (Weber 1920:146). My thanks to Sam Whimster who pointed this out to me during a conference on Weber and Foucault in Säo Paulo, May 2013. On this issue of Weber's sources, the anonymous referee for this Note informs us that the German translation of The Anxious Bench appeared in 1844 from the second and enlarged English edition and was accomplished probably by Nevin himself since he was one of the founding fathers of the so-called Mercersburg Theology, a German-American theological movement in the mid-19th century.© Max Weber Studies 2014, Clifton House, 17 Malvern Road, London, E8 3LP. 98 Max Weber Studies The 'anxious bench' was a conversion r Great Awakening', an evangelist reviva the United States in the nineteenth c revivalist movement constituted an innovative re-elaboration of cer tain practices employed by the Methodism in the eighteenth cen tury which, in turn, could be closely related to German pietism at the end of the seventeenth century. In the field of Protestant move ments derived straightforwardly from the Reformation, German pietism introduces, according to Weber, the sentiment factor, which was not part of the original Calvinist theology of predestination. Instead of projecting all rational conduct in this world to the pur suit of salvation in the Other World, German pietism intended to provide its followers full communion with God and his blessedness in this present world. Although this communion is mediated by the search for everyday asceticism, German pietism could result in a religiosity of a markedly hysterical character, by alternating frantic ecstasy and nervous lethargy, as Weber has pointed out. By rejecting the Calvinist presupposition of the particularism of grace, German pietism postulated that grace is universally distributed; its conces sion, however, is given to each man only once. If the moment of concession is passed by, grace would be lost forever and the follower would be in the same condition of those condemned by the arbi trary Calvinist predestination. As the decisive moment of receiving grace was undefined, German pietists invented a method for bring ing it about. Known as 'penitential battle', the method consisted of a devotional exercise in which sinners were encouraged to engage in a war against themselves and to regret their sins, a necessary condition to allow them to regenerate the heart and to receive the intended grace. Aimed at mass conversion, Methodism transforms the 'penitential battle' practice in an efficient mechanism to incite a sentimental experience of conversion. In North America, especially among Methodist sects and under revivalist movements of religious effervescence, the 'penitential battle' gains a particular and curious reconfiguration in...

ONLINE REVIEW MINING FOR FORECASTING SALES

The growing popularity of online product review for ums invites people to express opinions and sentimen ts toward the products .It gives the knowledge about the product as well as se ntiment of people towards the product. These online reviews are very important for forecasting the sales performance of product. In this paper, we discuss the online revie w mining techniques in movie domain. Sentiment PLSA which is responsible for fin ding hidden sentiment factors in the reviews and AR SA model used to predict sales performance. An Autoregressive Sentiment and Quality Aware model (ARSQA) also in consideration fbuild the quality for predicting sales performance. We propose cluste ring and classification based algorithm for sentime nt analysis.

Investor sentiment and bond risk premia

This article studies the statistical significance of the set of market sentiment variables proposed by Baker and Wurgler (2006) to predict the risk premium on U.S. sovereign bonds. We show that these variables can be summarized in one single market sentiment factor similar in spirit to the single-return forecasting factor proposed by Cochrane and Piazzesi (2005). Our findings reveal that this factor has predictive power beyond that contained in the yield curve and benchmark macroeconomic factors. The predictive power of this variable is time-varying, exhibiting more relevance during recession periods.

Mining Online Reviews for Predicting Sales Performance: A Case Study in the Movie Domain

Posting reviews online has become an increasingly popular way for people to express opinions and sentiments toward the products bought or services received. Analyzing the large volume of online reviews available would produce useful actionable knowledge that could be of economic values to vendors and other interested parties. In this paper, we conduct a case study in the movie domain, and tackle the problem of mining reviews for predicting product sales performance. Our analysis shows that both the sentiments expressed in the reviews and the quality of the reviews have a significant impact on the future sales performance of products in question. For the sentiment factor, we propose Sentiment PLSA (S-PLSA), in which a review is considered as a document generated by a number of hidden sentiment factors, in order to capture the complex nature of sentiments. Training an S-PLSA model enables us to obtain a succinct summary of the sentiment information embedded in the reviews. Based on S-PLSFA, we propose ARSA, an Autoregressive Sentiment-Aware model for sales prediction. We then seek to further improve the accuracy of prediction by considering the quality factor, with a focus on predicting the quality of a review in the absence of user-supplied indicators, and present ARSQA, an Autoregressive Sentiment and Quality Aware model, to utilize sentiments and quality for predicting product sales performance. Extensive experiments conducted on a large movie data set confirm the effectiveness of the proposed approach.

ASSET PRICING WITH INVESTOR SENTIMENT: EVIDENCE FROM CHINESE STOCK MARKETS*

We study the impact of investor sentiment on stock returns in China, using as a benchmark the three‐factor Fama–French model, and distinguishing between normal and positive sentiment. Sentiment helps explain the mis‐pricing component of returns in the Fama–French model and the time variation in the factors themselves. Factor loading patterns noted by Fama‐French are evident in China, but they can be equally well modelled by sentimental factors. Fama–French factors are less significant if factors are conditioned by sentiment, suggesting that in China sentiment affects both the way investors judge risks as well as portfolio returns directly.

Forecasting Inflation with Consumer Survey Data – Application of Multi-Group Confirmatory Factor Analysis to Elimination of the General Sentiment Factor

This paper (1) examines the properties of survey based households’ inflation expectations and investigates their forecasting performance. With application of the individual data from the State of the Households’ Survey (50 quarters between 1997Q4 and 2010Q1) it was shown that inflation expectations were affected by the consumer sentiment. Multi-Group Confirmatory Factor Analysis (MGCFA) was employed to verify whether a set of proxies provides a reliable basis for measurement of two latent phenomena – consumer sentiment and inflation expectations. Following the steps proposed by Davidov (2008) and Steenkamp and Baumgartner (1998), it appeared that it was possible to specify and estimate a MGCFA model with partial measurement invariance. Thus it was possible to eliminate the influence of consumer sentiment on inflation expectations and at the same time to obtain individually corrected answers concerning the inflation expectations. Additionally, it was shown that the linear relation between consumer sentiment and inflation expectations was stable over time. As a by-product of analysis, it was possible to show that respondents during the financial crisis were much less consistent in their answers to the questions of the consumer questionnaire. In the next step of the analysis, data on inflation expectations were applied to modelling and forecasting inflation. It was shown that with respect to standard ARIMA processes, inclusion of the information on the inflation expectations significantly improved the in-sample and out-of-sample forecasting performance of the time-series models. Especially out-of-sample performance was significantly better as the average absolute error in forecasts of headline and core inflation was reduced by half. It was also shown that models with inflation expectations based on the CFA method (after elimination of the consumer sentiment factor) provided better in-sample forecasts of inflation. Nevertheless, it was not confirmed for the out-of-sample forecasts. (1) Project financed by the National Bank of Poland. Polish title of the project: Prognozowanie inflacji na podstawie danych koniunktury gospodarstw domowych. Zastosowanie konfirmacyjnej analizy czynnikowej dla wielu grup do oczyszczenia prognoz inflacji z czynnika ogolnego nastroju gospodarczego.